Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is desirable to have a general pretrain model for versatile human-centric downstream tasks. This paper forges ahead along this path from the aspects of both benchmark and pretraining methods. Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting. To learn both coarse-grained and fine-grained knowledge in human bodies, we further propose a \textbf{P}rojector \textbf{A}ssis\textbf{T}ed \textbf{H}ierarchical pretraining method (\textbf{PATH}) to learn diverse knowledge at different granularity levels. Comprehensive evaluations on HumanBench show that our PATH achieves new state-of-the-art results on 17 downstream datasets and on-par results on the other 2 datasets. The code will be publicly at \href{https://github.com/OpenGVLab/HumanBench}{https://github.com/OpenGVLab/HumanBench}.
@article{arxiv.2303.05675,
title = {HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining},
author = {Shixiang Tang and Cheng Chen and Qingsong Xie and Meilin Chen and Yizhou Wang and Yuanzheng Ci and Lei Bai and Feng Zhu and Haiyang Yang and Li Yi and Rui Zhao and Wanli Ouyang},
journal= {arXiv preprint arXiv:2303.05675},
year = {2023}
}