Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensional outputs in object-level visual tasks. In this paper, we propose an object-centric vision framework, Obj2Seq. Obj2Seq takes objects as basic units, and regards most object-level visual tasks as sequence generation problems of objects. Therefore, these visual tasks can be decoupled into two steps. First recognize objects of given categories, and then generate a sequence for each of these objects. The definition of the output sequences varies for different tasks, and the model is supervised by matching these sequences with ground-truth targets. Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks. When experimenting on MS COCO, Obj2Seq achieves 45.7% AP on object detection, 89.0% AP on multi-label classification and 65.0% AP on human pose estimation. These results demonstrate its potential to be generally applied to different visual tasks. Code has been made available at: https://github.com/CASIA-IVA-Lab/Obj2Seq.
@article{arxiv.2209.13948,
title = {Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks},
author = {Zhiyang Chen and Yousong Zhu and Zhaowen Li and Fan Yang and Wei Li and Haixin Wang and Chaoyang Zhao and Liwei Wu and Rui Zhao and Jinqiao Wang and Ming Tang},
journal= {arXiv preprint arXiv:2209.13948},
year = {2022}
}
Comments
Accepted by NeurIPS 2022. Code available at https://github.com/CASIA-IVA-Lab/Obj2Seq