Blind reduction of speckle noise has become a long-standing unsolved problem in several imaging applications, such as medical ultrasound imaging, synthetic aperture radar (SAR) imaging, and underwater sonar imaging, etc. The unwanted noise could lead to negative effects on the reliable detection and recognition of objects of interest. From a statistical point of view, speckle noise could be assumed to be multiplicative, significantly different from the common additive Gaussian noise. The purpose of this study is to blindly reduce the speckle noise under non-ideal imaging conditions. The multiplicative relationship between latent sharp image and random noise will be first converted into an additive version through a logarithmic transformation. To promote imaging performance, we introduced the feature pyramid network (FPN) and atrous spatial pyramid pooling (ASPP), contributing to a more powerful deep blind DeSPeckling Network (named as DSPNet). In particular, DSPNet is mainly composed of two subnetworks, i.e., Log-NENet (i.e., noise estimation network in logarithmic domain) and Log-DNNet (i.e., denoising network in logarithmic domain). Log-NENet and Log-DNNet are, respectively, proposed to estimate noise level map and reduce random noise in logarithmic domain. The multi-scale mixed loss function is further proposed to improve the robust generalization of DSPNet. The proposed deep blind despeckling network is capable of reducing random noise and preserving salient image details. Both synthetic and realistic experiments have demonstrated the superior performance of our DSPNet in terms of quantitative evaluations and visual image qualities.

Deep neural network based object detection has become the cornerstone of many real-world applications. Along with this success comes concerns about its vulnerability to malicious attacks. To gain more insight into this issue, we propose a contextual camouflage attack (CCA for short) algorithm to influence the performance of object detectors. In this paper, we use an evolutionary search strategy and adversarial machine learning in interactions with a photo-realistic simulated environment to find camouflage patterns that are effective over a huge variety of object locations, camera poses, and lighting conditions. The proposed camouflages are validated effective to most of the state-of-the-art object detectors.

Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with cheap camera equipment, the low image quality, however, influences the classification accuracy, and freely available data bases cannot be exploited in a straight forward way to train classifiers to be used on a robot. As a solution we propose to train a network on degrading the quality images in order to mimic specific low quality imaging systems. Numerical experiments demonstrate that classification networks trained by using images produced by our quality degrading network along with the high quality images outperform classification networks trained only on high quality data when used on a real robot system, while being significantly easier to use than competing zero-shot domain adaptation techniques.

We present a reformulation of the regression and classification, which aims to validate the result of a machine learning algorithm. Our reformulation simplifies the original problem and validates the result of the machine learning algorithm using the training data. Since the validation of machine learning algorithms must always be explainable, we perform our experiments with the kNN algorithm as well as with an algorithm based on conditional probabilities, which is proposed in this work. For the evaluation of our approach, three publicly available data sets were used and three classification and two regression problems were evaluated. The presented algorithm based on conditional probabilities is also online capable and requires only a fraction of memory compared to the kNN algorithm.

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.

The analysis of Magnetic Resonance Imaging (MRI) sequences enables clinical professionals to monitor the progression of a brain tumor. As the interest for automatizing brain volume MRI analysis increases, it becomes convenient to have each sequence well identified. However, the unstandardized naming of MRI sequences make their identification difficult for automated systems, as well as make it difficult for researches to generate or use datasets for machine learning research. In face of that, we propose a system for identifying types of brain MRI sequences based on deep learning. By training a Convolutional Neural Network (CNN) based on 18-layer ResNet architecture, our system is able to classify a volumetric brain MRI as a T1, T1c, T2 or FLAIR sequence, or whether it does not belong to any of these classes. The network was trained with both pre-processed (BraTS dataset) and non-pre-processed (TCGA-GBM dataset) images with diverse acquisition protocols, requiring only a few layers of the volume for training. Our system is able to classify among sequence types with an accuracy of 96.27%.

Multi-agent reinforcement learning (MARL) is of importance for variable real-world applications but remains more challenges like stationarity and scalability. While recently value function factorization methods have obtained empirical good results in cooperative multi-agent environment, these works mostly focus on the decomposable learning structures. Inspired by the application of attention mechanism in machine translation and other related domains, we propose an attention based approach called attention value decomposition network (AVD-Net), which capitalizes on the coordination relations between agents. AVD-Net employs centralized training with decentralized execution (CTDE) paradigm, which factorizes the joint action-value functions with only local observations and actions of agents. Our method is evaluated on multi-agent particle environment (MPE) and StarCraft micromanagement environment (SMAC). The experiment results show the strength of our approach compared to existing methods with state-of-the-art performance in cooperative scenarios.

Eye tracking systems that estimate the point-of-gaze are essential in extended reality (XR) systems as they enable new interaction paradigms and technological improvements. It is important for these systems to maintain accuracy when the headset moves relative to the head (known as device slippage) due to head movements or user adjustment. One of the most accurate eye tracking techniques, which is also insensitive to shifts of the system relative to the head, uses two or more infrared (IR) light emitting diodes to illuminate the eye and an IR camera to capture images of the eye. An essential step in estimating the point-of-gaze in these systems is the precise determination of the location of two or more corneal reflections (virtual images of the IR-LEDs that illuminate the eye) in images of the eye. Eye trackers tend to have multiple light sources to ensure at least one pair of reflections for each gaze position. The use of multiple light sources introduces a difficult problem: the need to match the corneal reflections with the corresponding light source over the range of expected eye movements. Corneal reflection detection and matching often fail in XR systems due to the proximity of camera and steep illumination angles of light sources with respect to the eye. The failures are caused by corneal reflections having varying shape and intensity levels or disappearance due to rotation of the eye, or the presence of spurious reflections. We have developed a fully convolutional neural network, based on the UNET architecture, that solves the detection and matching problem in the presence of spurious and missing reflections. Eye images of 25 people were collected in a virtual reality headset using a binocular eye tracking module consisting of five infrared light sources per eye. A set of 4,000 eye images were manually labelled for each of the corneal reflections, and data augmentation was used to generate a dataset of 40,000 images. The network is able to correctly identify and match 91% of corneal reflections present in the test set. This is comparable to a state-of-the-art deep learning system, but our approach requires 33 times less memory and executes 10 times faster. The proposed algorithm, when used in an eye tracker in a VR system, achieved an average mean absolute gaze error of 1°. This is a significant improvement over the state-of-the-art learning-based XR eye tracking systems that have reported gaze errors of 2-3°.

Visual pose regression models estimate the camera pose from a query image with a single forward pass. Current models learn pose encoding from an image using deep convolutional networks which are trained per scene. The resulting encoding is typically passed to a multi-layer perceptron in order to regress the pose. In this work, we propose that scene-specific pose encoders are not required for pose regression and that encodings trained for visual similarity can be used instead. In order to test our hypothesis, we take a shallow architecture of several fully connected layers and train it with pre-computed encodings from a generic image retrieval model. We find that these encodings are not only sufficient to regress the camera pose, but that, when provided to a branching fully connected architecture, a trained model can achieve competitive results and even surpass current state-of-the-art pose regressors in some cases. Moreover, we show that for outdoor localization, the proposed architecture is the only pose regressor, to date, consistently localizing in under 2 meters and 5 degrees.

Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because: 1) the cipher alphabet changes from one document to another, 2) there is a lack of annotated corpus for training and 3) touching symbols make the symbol segmentation difficult and complex. To overcome these difficulties, we propose a novel method for handwritten ciphers recognition based on few-shot object detection. Our method first detects all symbols of a given alphabet in a line image, and then a decoding step maps the symbol similarity scores to the final sequence of transcribed symbols. By training on synthetic data, we show that the proposed architecture is able to recognize handwritten ciphers with unseen alphabets. In addition, if few labeled pages with the same alphabet are used for fine tuning, our method surpasses existing unsupervised and supervised HTR methods for ciphers recognition.

Deep reinforcement learning (DRL) has reached super human levels in complexes tasks like game solving (Go, StarCraft II), and autonomous driving. However, it remains an open question whether DRL can reach human level in applications to financial problems and in particular in detecting pattern crisis and consequently dis-investing. In this paper, we present an innovative DRL framework consisting in two sub-networks fed respectively with portfolio strategies past performances and standard deviation as well as additional contextual features. The second sub network plays an important role as it captures dependencies with common financial indicators features like risk aversion, economic surprise index and correlations between assets that allows taking into account context based information. We compare different network architectures either using layers of convolutions to reduce network's complexity or LSTM block to capture time dependency and whether previous allocations is important in the modeling. We also use adversarial training to make the final model more robust. Results on test set show this approach substantially over-performs traditional portfolio optimization methods like Markovitz and is able to detect and anticipate crisis like the current Covid one.

Scene text detection (STD) aims to locate text in images and plays an important role in many computer vision tasks including automatic driving and text recognition systems. Recently, deep neural networks (DNNs) have been widely and successfully used in scene text detection, leading to plenty of DNN-based STD methods including regression-based and segmentation-based STD methods. However, recent studies have also shown that DNN is vulnerable to adversarial attacks, which can significantly degrade the performance of DNN models. In this paper, we investigate the robustness of DNN-based STD methods against adversarial attacks. To this end, we propose a generic and efficient attack method to generate adversarial examples, which are produced by adding small but imperceptible adversarial perturbation to the input images. Experiments on attacking four various models and a real-world STD engine of Google optical character recognition (OCR) show that the state-of-the-art DNN-based STD methods including regression-based and segmentation-based methods are vulnerable to adversarial attacks.

Video-to-video face recognition in unconstrained conditions is still a very challenging problem, as the combination of several factors leads to an in general low-quality of facial frames. Besides, in some real contexts, the availability of labelled samples is limited, or data is streaming or it is only available temporarily due to storage constraints or privacy issues. In these cases, dealing with learning as an unsupervised incremental process is a feasible option. This work proposes a system based on dynamic ensembles of SVM's, which uses the ideas of self-training to perform adaptive Video-to-video face identification. The only label requirements of the system are a few frames (5 in our experiments) directly taken from the video-surveillance stream. The system will autonomously use additional video-frames to update and improve the initial model in an unsupervised way. Results show a significant improvement in comparison to other state-of-the-art static models.

Topological Data Analysis (TDA) is a rising field in machine learning. TDA considers the shape of data set. Persistence diagrams, one of main tools in TDA, store topological information about the data. Persistence curves, a recently developed framework, provides a canonical and flexible way to encode the information presented in persistence diagrams into vectors. Based on persistence curves, we (1) provide new sets of features for time series, (2) prove that these features are robust to noise, (3) propose a hybrid metric that takes both geometric and topological information of the time series into account. Finally, we apply these metrics to the UCR Time Series Classification Archive. These empirical results show that our metrics perform better than the relevant benchmark in most cases.

There has been growing interest recently in using machine learning techniques as an aid in clinical medicine. Machine learning offers a range of classification algorithms which can be applied to medical data to aid in making clinical predictions. Recent studies have demonstrated the high predictive accuracy of various classification algorithms applied to clinical data. Several studies have already been conducted in diagnosing or predicting chronic kidney disease at various stages using different sets of variables. In this study we are investigating the use machine learning techniques with blood test data. Such a system could aid renal teams in making recommendations to primary care general practitioners to refer patients to secondary care where patients may benefit from earlier specialist assessment and medical intervention. We are able to achieve an overall accuracy of 88.48\% using logistic regression, 87.12\% using ANN and 85.29\% using SVM. ANNs performed with the highest sensitivity at 89.74\% compared to 86.67\% for logistic regression and 85.51\% for SVM.

How to give agents the ability of continuous learning like human and animals is still a challenge. In the regularized continual learning method OWM, the constraint of the model on the energy compression of the learned task is ignored, which results in the poor performance of the method on the dataset with a large number of learning tasks. In this paper, we propose an energy minimization regularization(EMR) method to constrain the energy of learned tasks, providing enough learning space for the following tasks that are not learned, and increasing the capacity of the model to the number of learning tasks. A large number of experiments show that our method can effectively increase the capacity of the model and reduce the sensitivity of the model to the number of tasks and the size of the network.

In this work, we propose a method to simultaneously perform (i) biometric recognition (\textit{i.e.}, identify the individual), and (ii) device recognition, (\textit{i.e.}, identify the device) from a single biometric image, say, a face image, using a one-shot schema. Such a joint recognition scheme can be useful in devices such as smartphones for enhancing security as well as privacy. We propose to automatically learn a joint representation that encapsulates both biometric-specific and sensor-specific features. We evaluate the proposed approach using iris, face and periocular images acquired using near-infrared iris sensors and smartphone cameras. Experiments conducted using 14,451 images from 13 sensors resulted in a rank-1 identification accuracy of upto 99.81\% and a verification accuracy of upto 100\% at a false match rate of 1\%.

Visual Question Answering (VQA) is one of the most challenging emerging applications of deep learning. Providing powerful attention mechanisms is crucial for VQA, since the model must correctly identify the region of an image that is relevant to the question at hand. However, existing models analyze the input images at a fixed and typically small resolution, often leading to discarding valuable fine-grained details. To overcome this limitation, in this work we propose a reinforcement learning-based active perception approach that works by applying a series of transformation operations on the images (translation, zoom) in order to facilitate answering the question at hand. This allows for performing fine-grained analysis, effectively increasing the resolution at which the models process information. The proposed method is orthogonal to existing attention mechanisms and it can be combined with most existing VQA methods. The effectiveness of the proposed method is experimentally demonstrated on a challenging VQA dataset.

Mass utilization of body-worn cameras has led to a huge corpus of available egocentric video. Existing video summarization algorithms can accelerate browsing such videos by selecting (visually) interesting shots from them. Nonetheless, since the system user still has to watch the summary videos, browsing large video databases remain a challenge. Hence, in this work, we propose to generate a textual synopsis, consisting of a few sentences describing the most important events in a long egocentric videos. Users can read the short text to gain insight about the video, and more importantly, efficiently search through the content of a large video database using text queries. Since egocentric videos are long and contain many activities and events, using video-to-text algorithms results in thousands of descriptions, many of which are incorrect. Therefore, we propose a multi-task learning scheme to simultaneously generate descriptions for video segments and summarize the resulting descriptions in an end-to-end fashion. We Input a set of video shots and the network generates a text description for each shot. Next, visual-language content matching unit that is trained with a weakly supervised objective, identifies the correct descriptions. Finally, the last component of our network, called purport network, evaluates the descriptions all together to select the ones containing crucial information. Out of thousands of descriptions generated for the video, a few informative sentences are returned to the user. We validate our framework on the challenging UT Egocentric video dataset, where each video is between 3 to 5 hours long, associated with over 3000 textual descriptions on average. The generated textual summaries, including only 5 percent (or less) of the generated descriptions, are compared to groundtruth summaries in text domain using well-established metrics in natural language processing.

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity matrix is generated from data. In the second one, spectral clustering is applied on the affinity matrix. However, the affinity matrix produced by two-stage methods cannot fully reveal the similarity between data points from the same subspace, resulting in inaccurate clustering. Besides, most approaches fail to solve large-scale clustering problems due to poor efficiency. In this paper, we first propose a new scalable sparse method called Iterative Maximum Correlation (IMC) to learn the affinity matrix from data. Then we develop Piecewise Correlation Estimation (PCE) to densify the intra-subspace similarity produced by IMC. Finally we extend our work into a Sparse-Dense Subspace Clustering (SDSC) framework with a dense stage to optimize the affinity matrix for two-stage methods. We show that IMC is efficient for large-scale tasks, and PCE ensures better performance for IMC. We show the universality of our SDSC framework for current two-stage methods as well. Experiments on benchmark data sets demonstrate the effectiveness of our approaches.

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).