UniHCP: A Unified Model for Human-Centric Perceptions
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17840-17852
Abstract
Human-centric perceptions (e.g., pose estimation, human parsing, pedestrian detection, person re-identification, etc.) play a key role in industrial applications of visual models. While specific human-centric tasks have their own relevant semantic aspect to focus on, they also share the same underlying semantic structure of the human body. However, few works have attempted to exploit such homogeneity and design a general-propose model for human-centric tasks. In this work, we revisit a broad range of human-centric tasks and unify them in a minimalist manner. We propose UniHCP, a Unified Model for Human-Centric Perceptions, which unifies a wide range of human-centric tasks in a simplified end-to-end manner with the plain vision transformer architecture. With large-scale joint training on 33 human-centric datasets, UniHCP can outperform strong baselines on several in-domain and downstream tasks by direct evaluation. When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e.g., 69.8 mIoU on CIHP for human parsing, 86.18 mA on PA100K for attribute prediction, 90.3 mAP on Market1501 for ReID, and 85.8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task. The code and pretrained model are available at https://github.com/OpenGVLab/UniHCP.Keywords
All Related Versions
This publication has 69 references indexed in Scilit:
- End-to-End Comparative Attention Networks for Person Re-IdentificationIEEE Transactions on Image Processing, 2017
- Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-IdentificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Multi-label convolutional neural network based pedestrian attribute classificationImage and Vision Computing, 2017
- How Far are We from Solving Pedestrian Detection?2016
- Learning Mutual Visibility Relationship for Pedestrian Detection with a Deep ModelInternational Journal of Computer Vision, 2016
- Human Parsing with Contextualized Convolutional Neural Network2015
- Pedestrian detection aided by deep learning semantic tasks2015
- Pedestrian Attribute Recognition At Far Distance2014
- Unsupervised Salience Learning for Person Re-identification2013
- Pedestrian Detection: An Evaluation of the State of the ArtIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011