Xingyang Ni

Papers from this author

Adaptive L2 Regularization in Person Re-Identification

Xingyang Ni, Liang Fang, Heikki Juhani Huttunen
Track 5: Image and Signal Processing
Fri 15 Jan 2021 at 16:00 in session PS T5.8

Responsive image

Auto-TLDR; AdaptiveReID: Adaptive L2 Regularization for Person Re-identification

Underline Similar papers

We introduce an adaptive L2 regularization mechanism termed AdaptiveReID, in the setting of person re-identification. In the literature, it is common practice to utilize hand-picked regularization factors which remain constant throughout the training procedure. Unlike existing approaches, the regularization factors in our proposed method are updated adaptively through backpropagation. This is achieved by incorporating trainable scalar variables as the regularization factors, which are further fed into a scaled hard sigmoid function. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 datasets validate the effectiveness of our framework. Most notably, we obtain state-of-the-art performance on MSMT17, which is the largest dataset for person re-identification. Source code will be published at https://github.com/nixingyang/AdaptiveReID.

Loop-closure detection by LiDAR scan re-identification

Jukka Peltomäki, Xingyang Ni, Jussi Puura, Joni-Kristian Kamarainen, Heikki Juhani Huttunen
Track 3: Computer Vision Robotics and Intelligent Systems
Wed 13 Jan 2021 at 16:30 in session PS T3.6

Responsive image

Auto-TLDR; Loop-Closing Detection from LiDAR Scans Using Convolutional Neural Networks

Underline Similar papers

In this work, loop-closure detection from LiDAR scans is defined as an image re-identification problem. Re-identification is performed by computing Euclidean distances of a query scan to a gallery set of previous scans. The distances are computed in a feature embedding space where the scans are mapped by a convolutional neural network (CNN). The network is trained using the triplet loss training strategy. In our experiments we compare different backbone networks, variants of the triplet loss and generic and LiDAR specific data augmentation techniques. With a realistic indoor dataset the best architecture obtains the mean average precision (mAP) above 90%.