PBADet: A One-Stage Anchor-Free Approach for Part-Body Association

Zhongpai Gao, Huayi Zhou, Abhishek Sharma, Meng Zheng, Benjamin Planche, Terrence Chen, Ziyan Wu

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Human detection, part detection, association detection, anchor free

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: This paper presents PBADet, a novel one-stage, anchor-free approach for part-body association detection. We introduce a singular part-to-body center offset that effectively encapsulates the relationship between parts and the parent bodies.

Abstract: The detection of human parts (e.g., hands, face) and their correct association with individuals is an essential task, e.g., for ubiquitous human-machine interfaces and action recognition. Traditional methods often employ multi-stage processes, rely on cumbersome anchor-based systems, or do not scale well to larger part sets. This paper presents PBADet, a novel one-stage, anchor-free approach for part-body association detection. Building upon the anchor-free object representation across multi-scale feature maps, we introduce a singular part-to-body center offset that effectively encapsulates the relationship between parts and their parent bodies. Our design is inherently versatile and capable of managing multiple parts-to-body associations without compromising on detection accuracy or robustness. Comprehensive experiments on various datasets underscore the efficacy of our approach, which not only outperforms existing state-of-the-art techniques but also offers a more streamlined and efficient solution to the part-body association challenge.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: representation learning for computer vision, audio, language, and other modalities

Submission Number: 1346