Deep High-Resolution Representation Learning for Visual Recognition

Code

• github.com/open-mmlab/mmdetection
  In paperpytorch★ 32,525
• github.com/PaddlePaddle/PaddleDetection
  paddle★ 14,132
• github.com/open-mmlab/mmsegmentation
  pytorch★ 9,690
• github.com/PaddlePaddle/PaddleSeg
  paddle★ 9,319
• github.com/open-mmlab/mmpose
  pytorch★ 7,439
• github.com/PaddlePaddle/PaddleClas
  paddle★ 5,788
• github.com/CSAILVision/semantic-segmentation-pytorch
  pytorch★ 5,064
• github.com/mindspore-lab/mindone
  mindspore★ 464
• github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models
  tf★ 157
• github.com/mlpc-ucsd/PRTR
  pytorch★ 143

Abstract

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; (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.

Tasks

Benchmark Results

Reproductions