InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation

Dahu Shi, Xing Wei, Xiaodong Yu, Wenming Tan, Ye Ren, Shiliang Pu

Abstract

Multi-person pose estimation is an attractive and challenging task. Existing methods are mostly based on two-stage frameworks, which include top-down and bottom-up methods. Two-stage methods either suffer from high computational redundancy for additional person detectors or they need to group keypoints heuristically after predicting all the instance-agnostic keypoints. The single-stage paradigm aims to simplify the multi-person pose estimation pipeline and receives a lot of attention. However, recent single-stage methods have the limitation of low performance due to the difficulty of regressing various full-body poses from a single feature vector. Different from previous solutions that involve complex heuristic designs, we present a simple yet effective solution by employing instance-aware dynamic networks. Specifically, we propose an instance-aware module to adaptively adjust (part of) the network parameters for each instance. Our solution can significantly increase the capacity and adaptive-ability of the network for recognizing various poses, while maintaining a compact end-to-end trainable pipeline. Extensive experiments on the MS-COCO dataset demonstrate that our method achieves significant improvement over existing single-stage methods, and makes a better balance of accuracy and efficiency compared to the state-of-the-art two-stage approaches. The code and models are available at \url{https://github.com/hikvision-research/opera}.
BibTeX
@inproceedings{shi2021inspose,
  author = {Dahu Shi and Xing Wei and Xiaodong Yu and Wenming Tan and Ye Ren and Shiliang Pu},
  title = {{InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation}},
  booktitle = {ACM Multimedia},
  year = {2021},
  doi = {10.1145/3474085.3475447},
}

Loading related content...

Figure