Visual Recognition by Request

Chufeng Tang, Lingxi Xie, Xiaopeng Zhang, Xiaolin Hu, Qi Tian

CVPR 2023 pp. 15265-15274

doi:10.1109/CVPR52729.2023.01465 /cvpr/2023/tang2023cvpr-visual/

Abstract

Humans have the ability of recognizing visual semantics in an unlimited granularity, but existing visual recognition algorithms cannot achieve this goal. In this paper, we establish a new paradigm named visual recognition by request (ViRReq) to bridge the gap. The key lies in decomposing visual recognition into atomic tasks named requests and leveraging a knowledge base, a hierarchical and text-based dictionary, to assist task definition. ViRReq allows for (i) learning complicated whole-part hierarchies from highly incomplete annotations and (ii) inserting new concepts with minimal efforts. We also establish a solid baseline by integrating language-driven recognition into recent semantic and instance segmentation methods, and demonstrate its flexible recognition ability on CPP and ADE20K, two datasets with hierarchical whole-part annotations.

PDF CVPR Semantic Scholar

Cite

Text

Tang et al. "Visual Recognition by Request." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.01465

Markdown

[Tang et al. "Visual Recognition by Request." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/tang2023cvpr-visual/) doi:10.1109/CVPR52729.2023.01465

BibTeX

@inproceedings{tang2023cvpr-visual,
  title     = {{Visual Recognition by Request}},
  author    = {Tang, Chufeng and Xie, Lingxi and Zhang, Xiaopeng and Hu, Xiaolin and Tian, Qi},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {15265-15274},
  doi       = {10.1109/CVPR52729.2023.01465},
  url       = {https://mlanthology.org/cvpr/2023/tang2023cvpr-visual/}
}