HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
- 1 June 2020
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5385-5394
- https://doi.org/10.1109/cvpr42600.2020.00543
Abstract
Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene.Keywords
This publication has 22 references indexed in Scilit:
- Towards Accurate Multi-person Pose Estimation in the WildPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Feature Pyramid Networks for Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Realtime Multi-person 2D Pose Estimation Using Part Affinity FieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- RefineNet: Multi-path Refinement Networks for High-Resolution Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Multi-person Pose Estimation with Local Joint-to-Person AssociationsLecture Notes in Computer Science, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016