ICPR2020 Paper Browser

Paper download is intended for registered attendees only, and is subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.

A Novel Deep-Learning Pipeline for Light Field Image Based Material Recognition

Yunlong Wang, Kunbo Zhang, Zhenan Sun

Auto-TLDR; Factorize-Connect-Merge Deep Learning Pipeline for Light Field Image Based Material Recognition

Abstract Slides

The primitive basis of image based material recognition builds upon the fact that discrepancies in the reflectances of distinct materials lead to imaging differences under multiple viewpoints. LF cameras possess coherent abilities to capture multiple sub-aperture views (SAIs) within one exposure, which can provide appropriate multi-view sources for material recognition. In this paper, a unified ``Factorize-Connect-Merge`` (FCM) deep-learning pipeline is proposed to solve problems of light field image based material recognition. 4D light-field data as input is initially decomposed into consecutive 3D light-field slices. Shallow CNN is leveraged to extract low-level visual features of each view inside these slices. As to establish correspondences between these SAIs, Bidirectional Long-Short Term Memory (Bi-LSTM) network is built upon these low-level features to model the imaging differences. After feature selection including concatenation and dimension reduction, effective and robust feature representations for material recognition can be extracted from 4D light-field data. Experimental results indicate that the proposed pipeline can obtain remarkable performances on both tasks of single-pixel material classification and whole-image material segmentation. In addition, the proposed pipeline can potentially benefit and inspire other researchers who may also take LF images as input and need to extract 4D light-field representations for computer vision tasks such as object classification, semantic segmentation and edge detection.

Similar papers

Surface IR Reflectance Estimation and Material Recognition Using ToF Camera

Seokyeong Lee, Seungkyu Lee

Auto-TLDR; Material Type Recognition Using IR Reflectance Based Material Type Recognitions

Abstract Slides Poster Similar

Recently, various material recognition methods have been introduced that use a single color or light field camera. In prior methods, color and texture information of an object are used as key features. However, there exists fundamental limitation in using color features for material recognition in that material type can be characterized better by surface reflectance, visual appearance rather than its color and textures. In this work, we propose IR surface reflectance based material type recognition method. We use off-the-shelf ToF camera to estimate the IR reflectance of arbitrary surface. Material type recognition is performed on both color and surface IR reflectance features. Several network structures including gradual convolutional neural network are proposed and verified for our material recognition within our own 3D data sets.

5D Light Field Synthesis from a Monocular Video

Kyuho Bae, Andre Ivan, Hajime Nagahara, In Kyu Park

Auto-TLDR; Synthesis of Light Field Video from Monocular Video using Deep Learning

Abstract Slides Similar

Commercially available light field cameras have difficulty in capturing 5D (4D + time) light field videos. They can only capture still light filed images or are excessively expensive for normal users to capture the light field video. To tackle this problem, we propose a deep learning-based method for synthesizing a light field video from a monocular video. We propose a new synthetic light field video dataset that renders photorealistic scenes using Unreal Engine because no light field video dataset is available. The proposed deep learning framework synthesizes the light field video with a full set (9x9) of sub-aperture images from a normal monocular video. The proposed network consists of three sub-networks, namely, feature extraction, 5D light field video synthesis, and temporal consistency refinement. Experimental results show that our model can successfully synthesize the light field video for synthetic and real scenes and outperforms the previous frame-by-frame method quantitatively and qualitatively.

Fast and Efficient Neural Network for Light Field Disparity Estimation

Dizhi Ma, Andrew Lumsdaine

Auto-TLDR; Improving Efficient Light Field Disparity Estimation Using Deep Neural Networks

Abstract Slides Poster Similar

As with many imaging tasks, disparity estimation for light fields seems to be well-matched to machine learning approaches. Neural network-based methods can achieve an overall bad pixel rate as low as four percent on the 4D light field benchmark dataset,continued effort to improve accuracy is resulting in diminishing returns. On the other hand, due to the growing importance of mobile and embedded devices, improving the efficiency is emerging as an important problem. In this paper, we improve the efficiency of existing neural net approaches for light field disparity estimation by introducing efficient network blocks, pruning redundant sections of the network and downsampling the resolution of feature vector. To improve performance, we also propose densely sampled epipolar image plane volumes as input. Experiment results show that our approach can achieve similar results compared with state-of-the-art methods while using only one-tenth runtime.

Wavelet Attention Embedding Networks for Video Super-Resolution

Young-Ju Choi, Young-Woon Lee, Byung-Gyu Kim

Auto-TLDR; Wavelet Attention Embedding Network for Video Super-Resolution

Abstract Slides Poster Similar

Recently, Video super-resolution (VSR) has become more crucial as the resolution of display has been grown. The majority of deep learning-based VSR methods combine the convolutional neural networks (CNN) with motion compensation or alignment module to estimate high-resolution (HR) frame from low-resolution (LR) frames. However, most of previous methods deal with the spatial features equally and may result in the misaligned temporal features by pixel-based motion compensation and alignment module. It can lead to the damaging effect on the accuracy of the estimated HR feature. In this paper, we propose a wavelet attention embedding network (WAEN), including wavelet embedding network (WENet) and attention embedding network (AENet), to fully exploit the spatio-temporal informative features. The WENet is operated as a spatial feature extractor of individual low and high-frequency information based on 2-D Haar discrete wavelet transform. The meaningful temporal feature is extracted in the AENet through utilizing the weighted attention map between frames. Experimental results demonstrate that the proposed method achieves superior performance compared with state-of-the-art methods.

3D Semantic Labeling of Photogrammetry Meshes Based on Active Learning

Mengqi Rong, Shuhan Shen, Zhanyi Hu

Auto-TLDR; 3D Semantic Expression of Urban Scenes Based on Active Learning

Abstract Slides Poster Similar

As different urban scenes are similar but still not completely consistent, coupled with the complexity of labeling directly in 3D, high-level understanding of 3D scenes has always been a tricky problem. In this paper, we propose a procedural approach for 3D semantic expression of urban scenes based on active learning. We first start with a small labeled image set to fine-tune a semantic segmentation network and then project its probability map onto a 3D mesh model for fusion, finally outputs a 3D semantic mesh model in which each facet has a semantic label and a heat model showing each facet’s confidence. Our key observation is that our algorithm is iterative, in each iteration, we use the output semantic model as a supervision to select several valuable images for annotation to co-participate in the fine-tuning for overall improvement. In this way, we reduce the workload of labeling but not the quality of 3D semantic model. Using urban areas from two different cities, we show the potential of our method and demonstrate its effectiveness.

Cost Volume Refinement for Depth Prediction

João L. Cardoso, Nuno Goncalves, Michael Wimmer

Auto-TLDR; Refining the Cost Volume for Depth Prediction from Light Field Cameras

Abstract Slides Poster Similar

Light-field cameras are becoming more popular in the consumer market. Their data redundancy allows, in theory, to accurately refocus images after acquisition and to predict the depth of each point visible from the camera. Combined, these two features allow for the generation of full-focus images, which is impossible in traditional cameras. Multiple methods for depth prediction from light fields (or stereo) have been proposed over the years. A large subset of these methods relies on cost-volume estimates -- 3D objects where each layer represents a heuristic of whether each point in the image is at a certain distance from the camera. Generally, this volume is used to regress a disparity map, which is then refined for better results. In this paper, we argue that refining the cost volumes is superior to refining the disparity maps in order to further increase the accuracy of depth predictions. We propose a set of cost-volume refinement algorithms and show their effectiveness.

Multi-Scale Residual Pyramid Attention Network for Monocular Depth Estimation

Jing Liu, Xiaona Zhang, Zhaoxin Li, Tianlu Mao

Auto-TLDR; Multi-scale Residual Pyramid Attention Network for Monocular Depth Estimation

Abstract Slides Poster Similar

Monocular depth estimation is a challenging problem in computer vision and is crucial for understanding 3D scene geometry. Recently, deep convolutional neural networks (DCNNs) based methods have improved the estimation accuracy significantly. However, existing methods fail to consider complex textures and geometries in scenes, thereby resulting in loss of local details, distorted object boundaries, and blurry reconstruction. In this paper, we proposed an end-to-end Multi-scale Residual Pyramid Attention Network (MRPAN) to mitigate these problems.First,we propose a Multi-scale Attention Context Aggregation (MACA) module, which consists of Spatial Attention Module (SAM) and Global Attention Module (GAM). By considering the position and scale correlation of pixels from spatial and global perspectives, the proposed module can adaptively learn the similarity between pixels so as to obtain more global context information of the image and recover the complex structure in the scene. Then we proposed an improved Residual Refinement Module (RRM) to further refine the scene structure, giving rise to deeper semantic information and retain more local details. Experimental results show that our method achieves more promisin performance in object boundaries and local details compared with other state-of-the-art methods.

Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution

Xiaoyu Xiang, Qian Lin, Jan Allebach

Auto-TLDR; A Context-Aware Joint CAR and SR Neural Network for High-Resolution Text Recognition and Face Detection

Abstract Slides Poster Similar

Due to the limits of bandwidth and storage space, digital images are usually down-scaled and compressed when transmitted over networks, resulting in loss of details and jarring artifacts that can lower the performance of high-level visual tasks. In this paper, we aim to generate an artifact-free high-resolution image from a low-resolution one compressed with an arbitrary quality factor by exploring joint compression artifacts reduction (CAR) and super-resolution (SR) tasks. First, we propose a context-aware joint CAR and SR neural network (CAJNN) that integrates both local and non-local features to solve CAR and SR in one-stage. Finally, a deep reconstruction network is adopted to predict high quality and high-resolution images. Evaluation on CAR and SR benchmark datasets shows that our CAJNN model outperforms previous methods and also takes 26.2% less runtime. Based on this model, we explore addressing two critical challenges in high-level computer vision: optical character recognition of low-resolution texts, and extremely tiny face detection. We demonstrate that CAJNN can serve as an effective image preprocessing method and improve the accuracy for real-scene text recognition (from 85.30% to 85.75%) and the average precision for tiny face detection (from 0.317 to 0.611).

Free-Form Image Inpainting Via Contrastive Attention Network

Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Zhenhua Chai, Xiaolin Wei, Ran He

Auto-TLDR; Self-supervised Siamese inference for image inpainting

Abstract Slides Similar

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with sophisticated learning tasks. Specifically, in the image inpainting task, masks with any shapes can appear anywhere in images (i.e., free-form masks) forming complex patterns. It is difficult for encoders to capture such powerful representations under this complex situation. To tackle this problem, we propose a self-supervised Siamese inference network to improve the robustness and generalization. Moreover, the restored image usually can not be harmoniously integrated into the exiting content, especially in the boundary area. To address this problem, we propose a novel Dual Attention Fusion module (DAF), which can combine both the restored and known regions in a smoother way and be inserted into decoder layers in a plug-and-play way. DAF is developed to not only adaptively rescale channel-wise features by taking interdependencies between channels into account but also force deep convolutional neural networks (CNNs) focusing more on unknown regions. In this way, the unknown region will be naturally filled from the outside to the inside. Qualitative and quantitative experiments on multiple datasets, including facial and natural datasets (i.e., Celeb-HQ, Pairs Street View, Places2 and ImageNet), demonstrate that our proposed method outperforms against state-of-the-arts in generating high-quality inpainting results.

Global-Local Attention Network for Semantic Segmentation in Aerial Images

Minglong Li, Lianlei Shan, Weiqiang Wang

Auto-TLDR; GLANet: Global-Local Attention Network for Semantic Segmentation

Abstract Slides Poster Similar

Errors in semantic segmentation task could be classified into two types: large area misclassification and local inaccurate boundaries. Previously attention based methods capture rich global contextual information, this is beneficial to diminish the first type of error, but local imprecision still exists. In this paper we propose Global-Local Attention Network (GLANet) with a simultaneous consideration of global context and local details. Specifically, our GLANet is composed of two branches namely global attention branch and local attention branch, and three different modules are embedded in the two branches for the purpose of modeling semantic interdependencies in spatial, channel and boundary dimensions respectively. We sum the outputs of the two branches to further improve feature representation, leading to more precise segmentation results. The proposed method achieves very competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over baseline.

Residual Fractal Network for Single Image Super Resolution by Widening and Deepening

Jiahang Gu, Zhaowei Qu, Xiaoru Wang, Jiawang Dan, Junwei Sun

Auto-TLDR; Residual fractal convolutional network for single image super-resolution

Abstract Slides Poster Similar

The architecture of the convolutional neural network (CNN) plays an important role in single image super-resolution (SISR). However, most models proposed in recent years usually transplant methods or architectures that perform well in other vision fields. Thence they do not combine the characteristics of super-resolution (SR) and ignore the key information brought by the recurring texture feature in the image. To utilize patch-recurrence in SR and the high correlation of texture, we propose a residual fractal convolutional block (RFCB) and expand its depth and width to obtain residual fractal network (RFN), which contains deep residual fractal network (DRFN) and wide residual fractal network (WRFN). RFCB is recursive with multiple branches of magnified receptive field. Through the phased feature fusion module, the network focuses on extracting high-frequency texture feature that repeatedly appear in the image. We also introduce residual in residual (RIR) structure to RFCB that enables abundant low-frequency feature feed into deeper layers and reduce the difficulties of network training. RFN is the first supervised learning method to combine the patch-recurrence characteristic in SISR into network design. Extensive experiments demonstrate that RFN outperforms state-of-the-art SISR methods in terms of both quantitative metrics and visual quality, while the amount of parameters has been greatly optimized.

Automatical Enhancement and Denoising of Extremely Low-Light Images

Yuda Song, Yunfang Zhu, Xin Du

Auto-TLDR; INSNet: Illumination and Noise Separation Network for Low-Light Image Restoring

Abstract Slides Poster Similar

Deep convolutional neural networks (DCNN) based methodologies have achieved remarkable performance on various low-level vision tasks recently. Restoring images captured at night is one of the trickiest low-level vision tasks due to its high-level noise and low-level intensity. We propose a DCNN-based methodology, Illumination and Noise Separation Network (INSNet), which performs both denoising and enhancement on these extremely low-light images. INSNet fully utilizes global-ware features and local-ware features using the modified network structure and image sampling scheme. Compared to well-designed complex neural networks, our proposed methodology only needs to add a bypass network to the existing network. However, it can boost the quality of recovered images dramatically but only increase the computational cost by less than 0.1%. Even without any manual settings, INSNet can stably restore the extremely low-light images to desired high-quality images.

Hierarchically Aggregated Residual Transformation for Single Image Super Resolution

Zejiang Hou, Sy Kung

Auto-TLDR; HARTnet: Hierarchically Aggregated Residual Transformation for Multi-Scale Super-resolution

Abstract Slides Poster Similar

Visual patterns usually appear at different scales/sizes in natural images. Multi-scale feature representation is of great importance for the single-image super-resolution(SISR) task to reconstruct image objects at different scales.However, such characteristic has been rarely considered by CNN-based SISR methods. In this work, we propose a novel build-ing block, i.e. hierarchically aggregated residual transformation(HART), to achieve multi-scale feature representation in each layer of the network. Within each HART block, we connect multiple convolutions in a hierarchical residual-like manner, which greatly expands the range of effective receptive fields and helps to detect image features at different scales. To theoretically understand the proposed HART block, we recast SISR as an optimal control problem and show that HART effectively approximates the classical4th-order Runge-Kutta method, which has the merit of small local truncation error for solving numerical ordinary differential equation. By cascading the proposed HART blocks, we establish our high-performing HARTnet. Comparedwith existing SR state-of-the-arts (including those in NTIRE2019 SR Challenge leaderboard), the proposed HARTnet demonstrates consistent PSNR/SSIM performance improvements on various benchmark datasets under different degradation models.Moreover, HARTnet can efficiently restore more faithful high-resolution images than comparative SR methods (cf. Figure 1).

SAT-Net: Self-Attention and Temporal Fusion for Facial Action Unit Detection

Zhihua Li, Zheng Zhang, Lijun Yin

Auto-TLDR; Temporal Fusion and Self-Attention Network for Facial Action Unit Detection

Abstract Slides Poster Similar

Research on facial action unit detection has shown remarkable performances by using deep spatial learning models in recent years, however, it is far from reaching its full capacity in learning due to the lack of use of temporal information of AUs across time. Since the AU occurrence in one frame is highly likely related to previous frames in a temporal sequence, exploring temporal correlation of AUs across frames becomes a key motivation of this work. In this paper, we propose a novel temporal fusion and AU-supervised self-attention network (a so-called SAT-Net) to address the AU detection problem. First of all, we input the deep features of a sequence into a convolutional LSTM network and fuse the previous temporal information into the feature map of the last frame, and continue to learn the AU occurrence. Second, considering the AU detection problem is a multi-label classification problem that individual label depends only on certain facial areas, we propose a new self-learned attention mask by focusing the detection of each AU on parts of facial areas through the learning of individual attention mask for each AU, thus increasing the AU independence without the loss of any spatial relations. Our extensive experiments show that the proposed framework achieves better results of AU detection over the state-of-the-arts on two benchmark databases (BP4D and DISFA).

TinyVIRAT: Low-Resolution Video Action Recognition

Ugur Demir, Yogesh Rawat, Mubarak Shah

Auto-TLDR; TinyVIRAT: A Progressive Generative Approach for Action Recognition in Videos

Abstract Slides Poster Similar

The existing research in action recognition is mostly focused on high-quality videos where the action is distinctly visible. In real-world surveillance environments, the actions in videos are captured at a wide range of resolutions. Most activities occur at a distance with a small resolution and recognizing such activities is a challenging problem. In this work, we focus on recognizing tiny actions in videos. We introduce a benchmark dataset, TinyVIRAT, which contains natural low-resolution activities. The actions in TinyVIRAT videos have multiple labels and they are extracted from surveillance videos which makes them realistic and more challenging. We propose a novel method for recognizing tiny actions in videos which utilizes a progressive generative approach to improve the quality of low-resolution actions. The proposed method also consists of a weakly trained attention mechanism which helps in focusing on the activity regions in the video. We perform extensive experiments to benchmark the proposed TinyVIRAT dataset and observe that the proposed method significantly improves the action recognition performance over baselines. We also evaluate the proposed approach on synthetically resized action recognition datasets and achieve state-of-the-art results when compared with existing methods. The dataset and code will be publicly available.

P2D: A Self-Supervised Method for Depth Estimation from Polarimetry

Marc Blanchon, Desire Sidibe, Olivier Morel, Ralph Seulin, Daniel Braun, Fabrice Meriaudeau

Auto-TLDR; Polarimetric Regularization for Monocular Depth Estimation

Abstract Slides Poster Similar

Monocular depth estimation is a recurring subject in the ﬁeld of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we include a term of polarimetric regularization to state-of-the-art method to take speciﬁc advantage of the data. Our method is evaluated both qualitatively and quantitatively demonstrating that the contribution of this new information as well as an enhanced loss function improves depth estimation results, especially for specular areas.

Attentive Hybrid Feature Based a Two-Step Fusion for Facial Expression Recognition

Jun Weng, Yang Yang, Zichang Tan, Zhen Lei

Auto-TLDR; Attentive Hybrid Architecture for Facial Expression Recognition

Abstract Slides Poster Similar

Facial expression recognition is inherently a challenging task, especially for the in-the-wild images with various occlusions and large pose variations, which may lead to the loss of some crucial information. To address it, in this paper, we propose an attentive hybrid architecture (AHA) which learns global, local and integrated features based on different face regions. Compared with one type of feature, our extracted features own complementary information and can reduce the loss of crucial information. Specifically, AHA contains three branches, where all sub-networks in those branches employ the attention mechanism to further localize the interested pixels/regions. Moreover, we propose a two-step fusion strategy based on LSTM to deeply explore the hidden correlations among different face regions. Extensive experiments on four popular expression databases (i.e., CK+, FER-2013, SFEW 2.0, RAF-DB) show the effectiveness of the proposed method.

Video Lightening with Dedicated CNN Architecture

Li-Wen Wang, Wan-Chi Siu, Zhi-Song Liu, Chu-Tak Li, P. K. Daniel Lun

Auto-TLDR; VLN: Video Lightening Network for Driving Assistant Systems in Dark Environment

Abstract Slides Poster Similar

Darkness brings us uncertainty, worry and low confidence. This is a problem not only applicable to us walking in a dark evening but also for drivers driving a car on the road with very dim or even without lighting condition. To address this problem, we propose a new CNN structure named as Video Lightening Network (VLN) that regards the low-light enhancement as a residual learning task, which is useful as reference to indirectly lightening the environment, or for vision-based application systems, such as driving assistant systems. The VLN consists of several Lightening Back-Projection (LBP) and Temporal Aggregation (TA) blocks. Each LBP block enhances the low-light frame by domain transfer learning that iteratively maps the frame between the low- and normal-light domains. A TA block handles the motion among neighboring frames by investigating the spatial and temporal relationships. Several TAs work in a multi-scale way, which compensates the motions at different levels. The proposed architecture has a consistent enhancement for different levels of illuminations, which significantly increases the visual quality even in the extremely dark environment. Extensive experimental results show that the proposed approach outperforms other methods under both objective and subjective metrics.

Deep Iterative Residual Convolutional Network for Single Image Super-Resolution

Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni

Auto-TLDR; ISRResCNet: Deep Iterative Super-Resolution Residual Convolutional Network for Single Image Super-resolution

Abstract Slides Similar

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. Most recent deep learning based SISR methods focus on designing deeper / wider models to learn the non-linear mapping between low-resolution (LR) inputs and the high-resolution (HR) outputs. These existing SR methods do not take into account the image observation (physical) model and thus require a large number of network's trainable parameters with a huge volume of training data. To address these issues, we propose a deep Iterative Super-Resolution Residual Convolutional Network (ISRResCNet) that exploits the powerful image regularization and large-scale optimization techniques by training the deep network in an iterative manner with a residual learning approach. Extensive experimental results on various super-resolution benchmarks demonstrate that our method with a few trainable parameters improves results for different scaling factors in comparison with the state-of-art methods.

PSDNet: A Balanced Architecture of Accuracy and Parameters for Semantic Segmentation

Yue Liu, Zhichao Lian

Auto-TLDR; Pyramid Pooling Module with SE1Cblock and D2SUpsample Network (PSDNet)

Abstract Slides Poster Similar

Abstract—In this paper, we present our Pyramid Pooling Module （PPM） with SE1Cblock and D2SUpsample Network (PSDNet), a novel architecture for accurate semantic segmentation. Started from the known work called Pyramid Scene Parsing Network (PSPNet), PSDNet takes advantage of pyramid pooling structure with channel attention module and feature transform module in Pyramid Pooling Module (PPM). The enhanced PPM with these two components can strengthen context information flowing in the network instead of damaging it. The channel attention module we mentioned is an improved “Squeeze and Excitation with 1D Convolution” (SE1C) block which can explicitly model interrelationship between channels with fewer number of parameters. We propose a feature transform module named “Depth to Space Upsampling” (D2SUpsample) in the PPM which keeps integrity of features by transforming features while interpolating features, at the same time reducing parameters. In addition, we introduce a joint strategy in SE1Cblock which combines two variants of global pooling without increasing parameters. Compared with PSPNet, our work achieves higher accuracy on public datasets with 73.97% mIoU and 82.89% mAcc accuracy on Cityscapes Dataset based on ResNet50 backbone.

Extending Single Beam Lidar to Full Resolution by Fusing with Single Image Depth Estimation

Yawen Lu, Yuxing Wang, Devarth Parikh, Guoyu Lu

Auto-TLDR; Self-supervised LIDAR for Low-Cost Depth Estimation

Abstract Slides Similar

Depth estimation is playing an important role in indoor and outdoor scene understanding, autonomous driving, augmented reality and many other tasks. Vehicles and robotics are able to use active illumination sensors such as LIDAR to receive high precision depth estimation. However, high-resolution Lidars are usually too expensive, which limits its massive production on various applications. Though single beam LIDAR enjoys the benefits of low cost, one beam depth sensing is not usually sufficient to perceive the surrounding environment in many scenarios. In this paper, we propose a learning-based framework to explore to replicate similar or even higher performance as costly LIDARs with our designed self-supervised network and a low-cost single-beam LIDAR. After the accurate calibration with a visible camera, the single beam LIDAR can adjust the scale uncertainty of the depth map estimated by the visible camera. The adjusted depth map enjoys the benefits of high resolution and sensing accuracy as high beam LIDAR and maintains low-cost as single beam LIDAR. Thus we can achieve similar sensing effect of high beam LIDAR with more than a 50-100 times cheaper price (e.g., \$80000 Velodyne HDL-64E LIDAR v.s. \$1000 SICK TIM-781 2D LIDAR and normal camera). The proposed approach is verified on our collected dataset and public dataset with superior depth-sensing performance.

Multi-Direction Convolution for Semantic Segmentation

Dehui Li, Zhiguo Cao, Ke Xian, Xinyuan Qi, Chao Zhang, Hao Lu

Auto-TLDR; Multi-Direction Convolution for Contextual Segmentation

Abstract Slides Similar

Context is known to be one of crucial factors effecting the performance improvement of semantic segmentation. However, state-of-the-art segmentation models built upon fully convolutional networks are inherently weak in encoding contextual information because of stacked local operations such as convolution and pooling. Failing to capture context leads to inferior segmentation performance. Despite many context modules have been proposed to relieve this problem, they still operate in a local manner or use the same contextual information in different positions (due to upsampling). In this paper, we introduce the idea of Multi-Direction Convolution (MDC)—a novel operator capable of encoding rich contextual information. This operator is inspired by an observation that the standard convolution only slides along the spatial dimension (x, y direction) where the channel dimension (z direction) is fixed, which renders slow growth of the receptive field (RF). If considering the channel-fixed convolution to be one-direction, MDC is multi-direction in the sense that MDC slides along both spatial and channel dimensions, i.e., it slides along x, y when z is fixed, along x, z when y is fixed, and along y, z when x is fixed. In this way, MDC is able to encode rich contextual information with the fast increase of the RF. Compared to existing context modules, the encoded context is position-sensitive because no upsampling is required. MDC is also efficient and easy to implement. It can be implemented with few standard convolution layers with permutation. We show through extensive experiments that MDC effectively and selectively enlarges the RF and outperforms existing contextual modules on two standard benchmarks, including Cityscapes and PASCAL VOC2012.

Dynamic Guided Network for Monocular Depth Estimation

Xiaoxia Xing, Yinghao Cai, Yiping Yang, Dayong Wen

Auto-TLDR; DGNet: Dynamic Guidance Upsampling for Self-attention-Decoding for Monocular Depth Estimation

Abstract Slides Poster Similar

Self-attention or encoder-decoder structure has been widely used in deep neural networks for monocular depth estimation tasks. The former mechanism are capable to capture long-range information by computing the representation of each position by a weighted sum of the features at all positions, while the latter networks can capture structural details information by gradually recovering the spatial information. In this work, we combine the advantages of both methods. Specifically, our proposed model, DGNet, extends EMANet Network by adding an effective decoder module to refine the depth results. In the decoder stage, we further design dynamic guidance upsampling which uses local neighboring information of low-level features guide coarser depth to upsample. In this way, dynamic guidance upsampling generates content-dependent and spatially-variant kernels for depth upsampling which makes full use of spatial details information from low-level features. Experimental results demonstrate that our method obtains higher accuracy and generates the desired depth map.

LiNet: A Lightweight Network for Image Super Resolution

Armin Mehri, Parichehr Behjati Ardakani, Angel D. Sappa

Auto-TLDR; LiNet: A Compact Dense Network for Lightweight Super Resolution

Abstract Slides Poster Similar

This paper proposes a new lightweight network, LiNet, that enhancing technical efficiency in lightweight super resolution and operating approximately like very large and costly networks in terms of number of network parameters and operations. The proposed architecture allows the network to learn more abstract properties by avoiding low-level information via multiple links. LiNet introduces a Compact Dense Module, which contains set of inner and outer blocks, to efficiently extract meaningful information, to better leverage multi-level representations before upsampling stage, and to allow an efficient information and gradient flow within the network. Experiments on benchmark datasets show that the proposed LiNet achieves favorable performance against lightweight state-of-the-art methods.

A Multi-Task Neural Network for Action Recognition with 3D Key-Points

Rongxiao Tang, Wang Luyang, Zhenhua Guo

Auto-TLDR; Multi-task Neural Network for Action Recognition and 3D Human Pose Estimation

Abstract Slides Poster Similar

Action recognition and 3D human pose estimation are the fundamental problems in computer vision and closely related. In this work, we propose a multi-task neural network for action recognition and 3D human pose estimation. The results of the previous methods are still error-prone especially when tested against the images taken in-the-wild, leading error results in action recognition. To solve this problem, we propose a principled approach to generate high quality 3D pose ground truth given any in-the-wild image with a person inside. We achieve this by first devising a novel stereo inspired neural network to directly map any 2D pose to high quality 3D counterpart. Based on the high-quality 3D labels, we carefully design the multi-task framework for action recognition and 3D human pose estimation. The proposed architecture can utilize the shallow, deep features of the images, and the in-the-wild 3D human key-points to guide a more precise result. High quality 3D key-points can fully reflect the morphological features of motions, thus boosting the performance on action recognition. Experiments demonstrate that 3D pose estimation leads to significantly higher performance on action recognition than separated learning. We also evaluate the generalization ability of our method both quantitatively and qualitatively. The proposed architecture performs favorably against the baseline 3D pose estimation methods. In addition, the reported results on Penn Action and NTU datasets demonstrate the effectiveness of our method on the action recognition task.

Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition

Mirco Planamente, Andrea Bottino, Barbara Caputo

Auto-TLDR; A Single Stream Architecture for Egocentric Action Recognition from the First-Person Point of View

Abstract Slides Poster Similar

Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view. An open challenge in egocentric action recognition is that videos lack detailed information about the main actor's pose and thus tend to record only parts of the movement when focusing on manipulation tasks. Thus, the amount of information about the action itself is limited, making crucial the understanding of the manipulated objects and their context. Many previous works addressed this issue with two-stream architectures, where one stream is dedicated to modeling the appearance of objects involved in the action, and another to extracting motion features from optical flow. In this paper, we argue that learning features jointly from these two information channels is beneficial to capture the spatio-temporal correlations between the two better. To this end, we propose a single stream architecture able to do so, thanks to the addition of a self-supervised block that uses a pretext motion prediction task to intertwine motion and appearance knowledge. Experiments on several publicly available databases show the power of our approach.

Partially Supervised Multi-Task Network for Single-View Dietary Assessment

Ya Lu, Thomai Stathopoulou, Stavroula Mougiakakou

Auto-TLDR; Food Volume Estimation from a Single Food Image via Geometric Understanding and Semantic Prediction

Abstract Slides Poster Similar

Food volume estimation is an essential step in the pipeline of dietary assessment and demands the precise depth estimation of the food surface and table plane. Existing methods based on computer vision require either multi-image input or additional depth maps, reducing convenience of implementation and practical significance. Despite the recent advances in unsupervised depth estimation from a single image, the achieved performance in the case of large texture-less areas needs to be improved. In this paper, we propose a network architecture that jointly performs geometric understanding (i.e., depth prediction and 3D plane estimation) and semantic prediction on a single food image, enabling a robust and accurate food volume estimation regardless of the texture characteristics of the target plane. For the training of the network, only monocular videos with semantic ground truth are required, while the depth map and 3D plane ground truth are no longer needed. Experimental results on two separate food image databases demonstrate that our method performs robustly on texture-less scenarios and is superior to unsupervised networks and structure from motion based approaches, while it achieves comparable performance to fully-supervised methods.

Flow-Guided Spatial Attention Tracking for Egocentric Activity Recognition

Tianshan Liu, Kin-Man Lam

Auto-TLDR; flow-guided spatial attention tracking for egocentric activity recognition

Abstract Slides Poster Similar

The popularity of wearable cameras has opened up a new dimension for egocentric activity recognition. While some methods introduce attention mechanisms into deep learning networks to capture fine-grained hand-object interactions, they often neglect exploring the spatio-temporal relationships. Generating spatial attention, without adequately exploiting temporal consistency, will result in potentially sub-optimal performance in the video-based task. In this paper, we propose a flow-guided spatial attention tracking (F-SAT) module, which is based on enhancing motion patterns and inter-frame information, to highlight the discriminative features from regions of interest across a video sequence. A new form of input, namely the optical-flow volume, is presented to provide informative cues from moving parts for spatial attention tracking. The proposed F-SAT module is deployed to a two-branch-based deep architecture, which fuses complementary information for egocentric activity recognition. Experimental results on three egocentric activity benchmarks show that the proposed method achieves state-of-the-art performance.

EdgeNet: Semantic Scene Completion from a Single RGB-D Image

Aloisio Dourado, Teofilo De Campos, Adrian Hilton, Hansung Kim

Auto-TLDR; Semantic Scene Completion using 3D Depth and RGB Information

Abstract Slides Poster Similar

Semantic scene completion is the task of predicting a complete 3D representation of volumetric occupancy with corresponding semantic labels for a scene from a single point of view. In this paper, we present EdgeNet, a new end-to-end neural network architecture that fuses information from depth and RGB, explicitly representing RGB edges in 3D space. Previous works on this task used either depth-only or depth with colour by projecting 2D semantic labels generated by a 2D segmentation network into the 3D volume, requiring a two step training process. Our EdgeNet representation encodes colour information in 3D space using edge detection and flipped truncated signed distance, which improves semantic completion scores especially in hard to detect classes. We achieved state-of-the-art scores on both synthetic and real datasets with a simpler and a more computationally efficient training pipeline than competing approaches.

Modeling Extent-Of-Texture Information for Ground Terrain Recognition

Shuvozit Ghose, Pinaki Nath Chowdhury, Partha Pratim Roy, Umapada Pal

Auto-TLDR; Extent-of-Texture Guided Inter-domain Message Passing for Ground Terrain Recognition

Abstract Slides Poster Similar

Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image. In this paper, we propose a novel approach towards ground-terrain recognition via modeling the Extent-of-Texture information to establish a balance between the order-less texture component and ordered-spatial information locally. At first, the proposed method uses a CNN backbone feature extractor network to capture meaningful information of a ground terrain image, and model the extent of texture and shape information locally. Then, the order-less texture information and ordered shape information are encoded in a patch-wise manner, which is utilized by intra-domain message passing module to make every patch aware of each other for rich feature learning. Next, the Extent-of-Texture (EoT) Guided Inter-domain Message Passing module combines the extent of texture and shape information with the encoded texture and shape information in a patch-wise fashion for sharing knowledge to balance out the order-less texture information with ordered shape information. Further, Bilinear model generates a pairwise correlation between the order-less texture information and ordered shape information. Finally, the ground-terrain image classification is performed by a fully connected layer. The experimental results indicate superior performance of the proposed model over existing state-of-the-art techniques on publicly available datasets like DTD, MINC and GTOS-mobile.

Domain Siamese CNNs for Sparse Multispectral Disparity Estimation

David-Alexandre Beaupre, Guillaume-Alexandre Bilodeau

Auto-TLDR; Multispectral Disparity Estimation between Thermal and Visible Images using Deep Neural Networks

Abstract Slides Poster Similar

Multispectral disparity estimation is a difficult task for many reasons: it as all the same challenges as traditional visible-visible disparity estimation (occlusions, repetitive patterns, textureless surfaces), in addition of having very few common visual information between images (e.g. color information vs. thermal information). In this paper, we propose a new CNN architecture able to do disparity estimation between images from different spectrum, namely thermal and visible in our case. Our proposed model takes two patches as input and proceeds to do domain feature extraction for each of them. Features from both domains are then merged with two fusion operations, namely correlation and concatenation. These merged vectors are then forwarded to their respective classification heads, which are responsible for classifying the inputs as being same or not. Using two merging operations gives more robustness to our feature extraction process, which leads to more precise disparity estimation. Our method was tested using the publicly available LITIV 2014 and LITIV 2018 datasets, and showed best results when compared to other state of the art methods.

Enhanced Feature Pyramid Network for Semantic Segmentation

Mucong Ye, Ouyang Jinpeng, Ge Chen, Jing Zhang, Xiaogang Yu

Auto-TLDR; EFPN: Enhanced Feature Pyramid Network for Semantic Segmentation

Abstract Slides Poster Similar

Multi-scale feature fusion has been an effective way for improving the performance of semantic segmentation. However, current methods generally fail to consider the semantic gaps between the shallow (low-level) and deep (high-level) features and thus the fusion methods may not be optimal. In this paper, to address the issues of the semantic gap between the feature from different layers, we propose a unified framework based on the U-shape encoder-decoder architecture, named Enhanced Feature Pyramid Network (EFPN). Specifically, the semantic enhancement module (SEM), boundary extraction module (BEM), and context aggregation model (CAM) are incorporated into the decoder network to improve the robustness of the multi-level features aggregation. In addition, a global fusion model (GFM) in encoder branch is proposed to capture more semantic information in the deep layers and effectively transmit the high-level semantic features to each layer. Extensive experiments are conducted and the results show that the proposed framework achieves the state-of-the-art results on three public datasets, namely PASCAL VOC 2012, Cityscapes, and PASCAL Context. Furthermore, we also demonstrate that the proposed method is effective for other visual tasks that require frequent fusing features and upsampling.

RWF-2000: An Open Large Scale Video Database for Violence Detection

Ming Cheng, Kunjing Cai, Ming Li

Auto-TLDR; Flow Gated Network for Violence Detection in Surveillance Cameras

Abstract Slides Poster Similar

In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices. Usually, these cameras provide cues and evidence after crimes were conducted, while they are rarely used to prevent or stop criminal activities in time. It is both time and labor consuming to manually monitor a large amount of video data from surveillance cameras. Therefore, automatically recognizing violent behaviors from video signals becomes essential. In this paper, we summarize several existing video datasets for violence detection and propose a new video dataset with 2,000 videos all captured by surveillance cameras in real-world scenes. Also, we present a new method that utilizes both the merits of 3D-CNNs and optical flow, namely Flow Gated Network. The proposed approach obtains an accuracy of 87.25% on the test set of our proposed RWF-2000 database. The proposed database and source codes of this paper are currently open to access.

Boundary-Aware Graph Convolution for Semantic Segmentation

Hanzhe Hu, Jinshi Cui, Jinshi Hongbin Zha

Auto-TLDR; Boundary-Aware Graph Convolution for Semantic Segmentation

Abstract Slides Poster Similar

Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. However, few works have focused on harvesting boundary information to improve the segmentation performance. In order to enhance the feature similarity within the object and keep discrimination from other objects, we propose a boundary-aware graph convolution (BGC) module to propagate features within the object. The graph reasoning is performed among pixels of the same object apart from the boundary pixels. Based on the proposed BGC module, we further introduce the Boundary-aware Graph Convolution Network(BGCNet), which consists of two main components including a basic segmentation network and the BGC module, forming a coarse-to-fine paradigm. Specifically, the BGC module takes the coarse segmentation feature map as node features and boundary prediction to guide graph construction. After graph convolution, the reasoned feature and the input feature are fused together to get the refined feature, producing the refined segmentation result. We conduct extensive experiments on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff, and achieve state-of-the-art performance on all three benchmarks.

Progressive Splitting and Upscaling Structure for Super-Resolution

Qiang Li, Tao Dai, Shutao Xia

Auto-TLDR; PSUS: Progressive and Upscaling Layer for Single Image Super-Resolution

Abstract Slides Poster Similar

Recently, very deep convolutional neural networks (CNNs) have shown great success in single image super-resolution (SISR). Most of these methods focus on the design of network architecture and adopt a sub-pixel convolution layer at the end of network, but few have paid attention to exploring potential representation ability of upscaling layer. Sub-pixel convolution layer aggregates several low resolution (LR) feature maps and builds super-resolution (SR) images in a single step. However, those LR feature maps share similar patterns as they are extracted from a single trunk network. We believe that the mapping relationships between input image and each LR feature map are not consistent. Inspired by this, we propose a novel progressive splitting and upscaling structure, termed PSUS, which generates decoupled feature maps for upscaling layer to get better SR image. Experiments show that our method can not only speed up the convergence, but also achieve considerable improvement on image quality with fewer parameters and lower computational complexity.

Dual Path Multi-Modal High-Order Features for Textual Content Based Visual Question Answering

Yanan Li, Yuetan Lin, Hongrui Zhao, Donghui Wang

Auto-TLDR; TextVQA: An End-to-End Visual Question Answering Model for Text-Based VQA

Abstract Slides Similar

As a typical cross-modal problem, visual question answering (VQA) has received increasing attention from the communities of computer vision and natural language processing. Reading and reasoning about texts and visual contents in the images is a burgeoning and important research topic in VQA, especially for the visually impaired assistance applications. Given an image, it aims to predict an answer to a provided natural language question closely related to its textual contents. In this paper, we propose a novel end-to-end textual content based VQA model, which grounds question answering both on the visual and textual information. After encoding the image, question and recognized text words, it uses multi-modal factorized high-order modules and the attention mechanism to fuse question-image and question-text features respectively. The complex correlations among different features can be captured efficiently. To ensure the model's extendibility, it embeds candidate answers and recognized texts in a semantic embedding space and adopts semantic embedding based classifier to perform answer prediction. Extensive experiments on the newly proposed benchmark TextVQA demonstrate that the proposed model can achieve promising results.

VGG-Embedded Adaptive Layer-Normalized Crowd Counting Net with Scale-Shuffling Modules

Dewen Guo, Jie Feng, Bingfeng Zhou

Auto-TLDR; VadaLN: VGG-embedded Adaptive Layer Normalization for Crowd Counting

Abstract Slides Poster Similar

Crowd counting is widely used in real-time congestion monitoring and public security. Due to the limited data, many methods have little ability to be generalized because the differences between feature domains are not taken into consideration. We propose VGG-embedded adaptive layer normalization (VadaLN) to filter the features that irrelevant to the counting tasks in order that the counting results should not be affected by the image quality, color or illumination. VadaLN is implemented on the pretrained VGG-16 backbone. There is no additional learning parameters required through our method. VadaLN incoporates the proposed scale-shuffling modules (SSM) to relax the distortions in upsampling operations. Besides, non-aligned training methdology for the estimation of density maps is leveraged by an adversarial contextual loss (ACL) to improve the counting performance. Based on the proposed method, we construct an end-to-end trainable baseline model without bells and whistles, namely VadaLNet, which outperforms several recent state-of-the-art methods on commonly used challenging standard benchmarks. The intermediate scale-shuffled results are combined to formulate a scale-complementary strategy as a more powerful network, namely as VadaLNeSt. We implement VadaLNeSt on standard benchmarks, e.g. ShanghaiTech (Part A & Part B), UCF_CC_50, and UCF_QNRF, to show the superiority of our method.

MBD-GAN: Model-Based Image Deblurring with a Generative Adversarial Network

Li Song, Edmund Y. Lam

Auto-TLDR; Model-Based Deblurring GAN for Inverse Imaging

Abstract Slides Poster Similar

This paper presents a methodology to tackle inverse imaging problems by leveraging the synergistic power of imaging model and deep learning. The premise is that while learning-based techniques have quickly become the methods of choice in various applications, they often ignore the prior knowledge embedded in imaging models. Incorporating the latter has the potential to improve the image estimation. Specifically, we first provide a mathematical basis of using generative adversarial network (GAN) in inverse imaging through considering an optimization framework. Then, we develop the specific architecture that connects the generator and discriminator networks with the imaging model. While this technique can be applied to a variety of problems, from image reconstruction to super-resolution, we take image deblurring as the example here, where we show in detail the implementation and experimental results of what we call the model-based deblurring GAN (MBD-GAN).

Single View Learning in Action Recognition

Gaurvi Goyal, Nicoletta Noceti, Francesca Odone

Auto-TLDR; Cross-View Action Recognition Using Domain Adaptation for Knowledge Transfer

Abstract Slides Poster Similar

Viewpoint is an essential aspect of how an action is visually perceived, with the motion appearing substantially different for some viewpoint pairs. Data driven action recognition algorithms compensate for this by including a variety of viewpoints in their training data, adding to the cost of data acquisition as well as training. We propose a novel methodology that leverages deeply pretrained features to learn actions from a single viewpoint using domain adaptation for knowledge transfer. We demonstrate the effectiveness of this pipeline on 3 different datasets: IXMAS, MoCA and NTU RGBD+, and compare with both classical and deep learning methods. Our method requires low training data and demonstrates unparalleled cross-view action recognition accuracies for single view learning.

Learning Non-Rigid Surface Reconstruction from Spatio-Temporal Image Patches

Matteo Pedone, Abdelrahman Mostafa, Janne Heikkilä

Auto-TLDR; Dense Spatio-Temporal Depth Maps of Deformable Objects from Video Sequences

Abstract Slides Poster Similar

We present a method to reconstruct a dense spatio-temporal depth map of a non-rigidly deformable object directly from a video sequence. The estimation of depth is performed locally on spatio-temporal patches of the video, and then the full depth video of the entire shape is recovered by combining them together. Since the geometric complexity of a local spatio-temporal patch of a deforming non-rigid object is often simple enough to be faithfully represented with a parametric model, we artificially generate a database of small deforming rectangular meshes rendered with different material properties and light conditions, along with their corresponding depth videos, and use such data to train a convolutional neural network. We tested our method on both synthetic and Kinect data and experimentally observed that the reconstruction error is significantly lower than the one obtained using other approaches like conventional non-rigid structure from motion.

ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition

Qi Song, Qianyi Jiang, Xiaolin Wei, Nan Li, Rui Zhang

Auto-TLDR; ReADS: Rectified Attentional Double Supervised Network for General Scene Text Recognition

Abstract Slides Poster Similar

In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem while they may fail in some scenarios respectively. CTC concentrates more on every individual character but is weak in text semantic dependency modeling. Attn based methods have better context semantic modeling ability while tends to overfit on limited training data. In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReADS) for general scene text recognition. To overcome the weakness of CTC and Attn, both of them are applied in our method but with different modules in two supervised branches which can make a complementary to each other. Moreover, effective spatial and channel attention mechanisms are introduced to eliminate background noise and extract valid foreground information. Finally, a simple rectified network is implemented to rectify irregular text. The ReADS can be trained end-to-end and only word-level annotations are required. Extensive experiments on various benchmarks verify the effectiveness of ReADS which achieves state-of-the-art performance.

PointSpherical: Deep Shape Context for Point Cloud Learning in Spherical Coordinates

Hua Lin, Bin Fan, Yongcheng Liu, Yirong Yang, Zheng Pan, Jianbo Shi, Chunhong Pan, Huiwen Xie

Auto-TLDR; Spherical Hierarchical Modeling of 3D Point Cloud

Abstract Slides Poster Similar

We propose Spherical Hierarchical modeling of 3D point cloud. Inspired by Shape Context, we design a receptive field on each 3D point by placing a spherical coordinate on it. We sample points using the furthest point method and creating overlapping balls of points. For each ball, we divide the space into radial, polar angular and azimuthal angular bins on which we form a Spherical Hierarchy. We apply 1x1 CNN convolution on points to start the initial feature extraction. Repeated 3D CNN and max pooling over the Spherical bins propagate contextual information until all the information is condensed in the center bin. Extensive experiments on five datasets strongly evidence that our method outperform current models on various Point Cloud Learning tasks, including 2D/3D shape classification, 3D part segmentation and 3D semantic segmentation.

Context-Aware Residual Module for Image Classification

Jing Bai, Ran Chen

Auto-TLDR; Context-Aware Residual Module for Image Classification

Abstract Slides Poster Similar

Attention module has achieved great success in numerous vision tasks. However, existing visual attention modules generally consider the features of a single-scale, and cannot make full use of their multi-scale contextual information. Meanwhile, the multi-scale spatial feature representation has demonstrated its outstanding performance in a wide range of applications. However, the multi-scale features are always represented in a layer-wise manner, i.e. it is impossible to know their contextual information at a granular level. Focusing on the above issue, a context-aware residual module for image classification is proposed in this paper. It consists of a novel multi-scale channel attention module MSCAM to learn refined channel weights by considering the visual features of its own scale and its surrounding fields, and a multi-scale spatial aware module MSSAM to further capture more spatial information. Either or both of the two modules can be plugged into any CNN-based backbone image classification architecture with a short residual connection to obtain the context-aware enhanced features. The experiments on public image recognition datasets including CIFAR10, CIFAR100，Tiny-ImageNet and ImageNet consistently demonstrate that our proposed modules significantly outperforms a wide-used state-of-the-art methods, e.g., ResNet and the lightweight networks of MobileNet and SqueezeeNet.

Detail-Revealing Deep Low-Dose CT Reconstruction

Xinchen Ye, Yuyao Xu, Rui Xu, Shoji Kido, Noriyuki Tomiyama

Auto-TLDR; A Dual-branch Aggregation Network for Low-Dose CT Reconstruction

Abstract Slides Poster Similar

Low-dose CT imaging emerges with low radiation risk due to the reduction of radiation dose, but brings negative impact on the imaging quality. This paper addresses the problem of low-dose CT reconstruction. Previous methods are unsatisfactory due to the inaccurate recovery of image details under the strong noise generated by the reduction of radiation dose, which directly affects the final diagnosis. To suppress the noise effectively while retain the structures well, we propose a detail-revealing dual-branch aggregation network to effectively reconstruct the degraded CT image. Specifically, the main reconstruction branch iteratively exploits and compensates the reconstruction errors to gradually refine the CT image, while the prior branch is to learn the structure details as prior knowledge to help recover the CT image. A sophisticated detail-revealing loss is designed to fuse the information from both branches and guide the learning to obtain better performance from pixel-wise and holistic perspectives respectively. Experimental results show that our method outperforms the state-of-art methods in both PSNR and SSIM metrics.

Two-Level Attention-Based Fusion Learning for RGB-D Face Recognition

Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad

Auto-TLDR; Fused RGB-D Facial Recognition using Attention-Aware Feature Fusion

Abstract Slides Poster Similar

With recent advances in RGB-D sensing technologies as well as improvements in machine learning and fusion techniques, RGB-D facial recognition has become an active area of research. A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition. The proposed method first extracts features from both modalities using a convolutional feature extractor. These features are then fused using a two layer attention mechanism. The first layer focuses on the fused feature maps generated by the feature extractor, exploiting the relationship between feature maps using LSTM recurrent learning. The second layer focuses on the spatial features of those maps using convolution. The training database is preprocessed and augmented through a set of geometric transformations, and the learning process is further aided using transfer learning from a pure 2D RGB image training process. Comparative evaluations demonstrate that the proposed method outperforms other state-of-the-art approaches, including both traditional and deep neural network-based methods, on the challenging CurtinFaces and IIIT-D RGB-D benchmark databases, achieving classification accuracies over 98.2% and 99.3% respectively. The proposed attention mechanism is also compared with other attention mechanisms, demonstrating more accurate results.

Single Image Super-Resolution with Dynamic Residual Connection

Karam Park, Jae Woong Soh, Nam Ik Cho

Auto-TLDR; Dynamic Residual Attention Network for Lightweight Single Image Super-Residual Networks

Abstract Slides Poster Similar

Deep convolutional neural networks have shown significant improvement in the single image super-resolution (SISR) field. Recently, there have been attempts to solve the SISR problem using lightweight networks, considering limited computational resources for real-world applications. Especially for lightweight networks, balancing between parameter demand and performance is very difficult to adjust, and most lightweight SISR networks are manually designed based on a huge number of brute-force experiments. Besides, a critical key to the network performance relies on the skip connection of building blocks that are repeatedly in the architecture. Notably, in previous works, these connections are pre-defined and manually determined by human researchers. Hence, they are less flexible to the input image statistics, and there can be a better solution for the given number of parameters. Therefore, we focus on the automated design of networks regarding the connection of basic building blocks (residual networks), and as a result, propose a dynamic residual attention network (DRAN). The proposed method allows the network to dynamically select residual paths depending on the input image, based on the idea of attention mechanism. For this, we design a dynamic residual module that determines the residual paths between the basic building blocks for the given input image. By finding optimal residual paths between the blocks, the network can selectively bypass informative features needed to reconstruct the target high-resolution (HR) image. Experimental results show that our proposed DRAN outperforms most of the existing state-of-the-arts lightweight models in SISR.

Improving Low-Resolution Image Classification by Super-Resolution with Enhancing High-Frequency Content

Liguo Zhou, Guang Chen, Mingyue Feng, Alois Knoll

Auto-TLDR; Super-resolution for Low-Resolution Image Classification

Abstract Slides Poster Similar

With the prosperous development of Convolutional Neural Networks, currently they can perform excellently on visual understanding tasks when the input images are high quality and common quality images. However, large degradation in performance always occur when the input images are low quality images. In this paper, we propose a new super-resolution method in order to improve the classification performance for low-resolution images. In an image, the regions in which pixel values vary dramatically contain more abundant high frequency contents compared to other parts. Based on this fact, we design a weight map and integrate it with a super-resolution CNN training framework. During the process of training, this weight map can find out positions of the high frequency pixels in ground truth high-resolution images. After that, the pixel-level loss function takes effect only at these found positions to minimize the difference between reconstructed high-resolution images and ground truth high-resolution images. Compared with other state-of-the-art super-resolution methods, the experiment results show that our method can recover more high-frequency contents in high-resolution image reconstructing, and better improve the classification accuracy after low-resolution image preprocessing.

Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization

Negin Ghamsarian, Mario Taschwer, Doris Putzgruber, Stephanie. Sarny, Klaus Schoeffmann

Auto-TLDR; relevance-based retrieval in cataract surgery videos

Abstract Slides Similar

In cataract surgery, the operation is performed with the help of a microscope. Since the microscope enables watching real-time surgery by up to two people only, a major part of surgical training is conducted using the recorded videos. To optimize the training procedure with the video content, the surgeons require an automatic relevance detection approach. In addition to relevance-based retrieval, these results can be further used for skill assessment and irregularity detection in cataract surgery videos. In this paper, a three-module framework is proposed to detect and classify the relevant phase segments in cataract videos. Taking advantage of an idle frame recognition network, the video is divided into idle and action segments. To boost the performance in relevance detection Mask R-CNN is utilized to detect the cornea in each frame where the relevant surgical actions are conducted. The spatio-temporal localized segments containing higher-resolution information about the pupil texture and actions, and complementary temporal information from the same phase are fed into the relevance detection module. This module consists of four parallel recurrent CNNs being responsible to detect four relevant phases that have been defined with medical experts. The results will then be integrated to classify the action phases as irrelevant or one of four relevant phases. Experimental results reveal that the proposed approach outperforms static CNNs and different configurations of feature-based and end-to-end recurrent networks.