VALSE 论文速览 第138期：HumanBench:Towards General Human-centric Models

论文题目：HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

作者列表：

Shixiang Tang (悉尼大学), Cheng Chen (商汤科技), Qingsong Xie (商汤科技), Meilin Chen (浙江大学), Yizhou Wang (浙江大学), Yuanzheng Ci (悉尼大学), Lei Bai (悉尼大学), Feng Zhu (商汤科技), Haiyang Yang (商汤科技), Li Yi (商汤科技), Rui Zhao (商汤科技), Wanli Ouyang (悉尼大学)

B站观看网址：

https://www.bilibili.com/video/BV128411k7WD/

论文摘要：

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 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 Projector AssisTed Hierarchical pretraining method (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. 

论文信息：

[1] Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang, HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining, Accepted in CVPR2023.

论文链接：

[https://arxiv.org/abs/2303.05675]

代码链接：

[https://github.com/OpenGVLab/HumanBench]

视频讲者简介：

唐诗翔，悉尼大学信息科学与工程学院博士生。主要研究方向为无监督学习、以人为中心的通才模型研发。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：秦杰 (南京航空航天大学)

季度轮值AC：叶茫 (武汉大学)