Deep-High-Resolution Representation Learning for Cross-Resolution Person Re-identification
Journal of IEEE Transactions on Multimedia | arXiv:3660003 [cs.CV] 21 Mar 2021
Contents 📋
Introduction 🔖
We propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the cross-resolution person re-ID problem. Specifically, in order to restore the resolution of low-resolution images and make reasonable use of different channel information of feature maps, we introduce and innovate VDSR module with channel attention (CA) mechanism, named as VDSR-CA. Then we reform the HRNet by designing a novel representation head to extract discriminating features, named as HRNet-ReID. In addition, a pseudo-siamese framework is constructed to reduce the difference of feature distributions between low-resolution images and high-resolution images. The experimental results on five cross-resolution person datasets verify the effectiveness of our proposed approach. Compared with the state-of-the-art methods, our proposed PS-HRNet improves 3.4%, 6.2%, 2.5%,1.1% and 4.2% at Rank-1 on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively.
Usage
We use apex (A PyTorch Extension) a Pytorch extension with NVIDIA-maintained utilities to streamline mixed precision and distributed training. Some of the code here will be included in upstream Pytorch eventually. The intention of Apex is to make up-to-date utilities available to users as quickly as possible.Installation instructions can be found here: https://github.com/NVIDIA/apex#quick-start.
We display the process of the algorithm as an ipynb file, you can use jupyter notebook to view and run it.
You may need HRNet-W32-C ImageNet pretrained models or learn more about HRNet: https://github.com/HRNet/HRNet-Image-Classification.git.
Results 🏆
