Deep High-Resolution Representation Learning for Visual Recognition
Jingdong Wang, Ke Sun, Tianheng Cheng et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at https://github.com/HRNet.
Cited by 4,785 works. doi:10.1109/tpami.2020.2983686
Authors
- Jingdong Wang
- Ke Sun
- Tianheng Cheng
- Borui Jiang
- Chaorui Deng
- Yang Sheng Zhao
- Dong Liu
- Yadong Mu
- Mingkui Tan
- Xinggang Wang
- Wenyu Liu
- Bin Xiao
References
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Going deeper with convolutions
- Adam: A Method for Stochastic Optimization
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Fully convolutional networks for semantic segmentation
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)