AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

Ke Zhu, Jianxin Wu

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 204 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add class-specific spatial pooling to average pooling (ablation)CSRA ResNet-cut · MS-COCOmAP (%): 82.1 -> 85.3Improved
use spatial pooling alone versus combining with average pooling (ablation)CSRA ResNet-cut · MS-COCOmAP (%): 84.2 -> 85.3Improved
add the residual average-pooling term to spatial pooling (ablation)CSRA ResNet-cut · MS-COCOmAP (%): 82.1 -> 84.2Improved
increase attention heads from 1 to 8 (ablation)CSRA VIT-L16 · MS-COCOmAP (%): 85.8 -> 86.5Improved
increase attention heads from 1 to 6 (ablation)CSRA ResNet-cut · MS-COCOmAP (%): 85.3 -> 85.6Improved
add classifier normalization (H=2) (ablation)CSRA ResNet-101 · MS-COCOmAP (%): 83.1 -> 83.2No clear effect
add classifier normalization (H=4) (ablation)CSRA ResNet-101 · MS-COCOmAP (%): 83.4 -> 83.3No clear effect
add CSRA to VIT-L16VIT-L16 · MS-COCOmAP (%): 80.4 -> 86.5Improved
add CSRA to ResNet-101ResNet-101 · MS-COCOmAP (%): 79.4 -> 83.5Improved
add CSRA to VIT-B16VIT-B16 · WIDER-AttributemAP (%): 86.3 -> 89.0Improved
add RandAugment to CSRAVIT-L16 + CSRA · MS-COCOmAP (%): 86.5 -> 86.9Improved
add training-free test-time global max pooling to average poolingMobileNet · MS-COCOmAP (%): 71.8 -> 73.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy