备注

您正在阅读 MMClassification 0.x 版本的文档。MMClassification 0.x 会在 2022 年末被切换为次要分支。建议您升级到 MMClassification 1.0 版本，体验更多新特性和新功能。请查阅 MMClassification 1.0 的安装教程、迁移教程以及更新日志。

CSRA

Residual Attention: A Simple but Effective Method for Multi-Label Recognition

Abstract

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively capture different spatial regions occupied by objects from different categories, we propose an embarrassingly simple module, named class-specific residual attention (CSRA). CSRA generates class-specific features for every category by proposing a simple spatial attention score, and then combines it with the class-agnostic average pooling feature. CSRA achieves state-of-the-art results on multilabel recognition, and at the same time is much simpler than them. Furthermore, with only 4 lines of code, CSRA also leads to consistent improvement across many diverse pretrained models and datasets without any extra training. CSRA is both easy to implement and light in computations, which also enjoys intuitive explanations and visualizations.

Results and models

VOC2007

Model	Pretrain	Params(M)	Flops(G)	mAP	OF1 (%)	CF1 (%)	Config	Download
Resnet101-CSRA	ImageNet-1k	23.55	4.12	94.98	90.80	89.16	config	model | log

Citation

@misc{https://doi.org/10.48550/arxiv.2108.02456,
  doi = {10.48550/ARXIV.2108.02456},
  url = {https://arxiv.org/abs/2108.02456},
  author = {Zhu, Ke and Wu, Jianxin},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Residual Attention: A Simple but Effective Method for Multi-Label Recognition},
  publisher = {arXiv},
  year = {2021},
  copyright = {arXiv.org perpetual, non-exclusive license}
}