AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization

Wei Gao, Fang Wan, Xingjia Pan, Zhiliang Peng, Qi Tian, Zhenjun Han, Bolei Zhou, Qixiang Ye

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 244 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 semantic-aware map to attention (couple them) (ablation)TransAttention · CUB-200-2011Top-1 Loc Acc: 58.9 -> 71.3Improved
add attention map to semantic-aware map (couple them) (ablation)TransCAM · CUB-200-2011Top-1 Loc Acc: 17.7 -> 71.3Improved
add semantic-aware map to attention (couple them) (ablation)TransAttention · ILSVRCTop-1 Loc Acc: 43.0 -> 53.4Improved
add attention to semantic-aware map (ablation)TransCAM · ILSVRCTop-1 Loc Acc: 34.9 -> 53.4Improved
use Conv2D instead of FC for semantic-aware map (ablation)TS-CAM · ILSVRCTop-1 Loc Acc: 31.5 -> 53.4Improved
use Conv2D instead of FC (ablation)TS-CAM · CUB-200-2011Top-1 Loc Acc: 69.4 -> 71.3Improved
use Conv2D instead of Conv1D (ablation)TS-CAM · ILSVRCTop-1 Loc Acc: 49.8 -> 53.4Improved
sum attention maps from all 12 layers instead of 8 (ablation)TS-CAM · CUB-200-2011Top-1 Loc Acc: 65.2 -> 71.3Improved
sum attention maps from all 12 layers instead of 8 (ablation)TS-CAM · ILSVRCTop-1 Loc Acc: 49.4 -> 53.4Improved
replace CNN CAM with TS-CAM on DeiT-SCAM (VGG16) · CUB-200-2011Top-1 Loc Acc: 44.2 -> 71.3Improved
replace CAM InceptionV3 with TS-CAMCAM (InceptionV3) · ILSVRCTop-1 Loc Acc: 46.3 -> 53.4Improved
replace CAM InceptionV3 with TS-CAMCAM (InceptionV3) · CUB-200-2011Part error: 23.09 -> 6.30Improved

Later papers that compared with this method

9 later accepted papers report TS-CAM as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

1 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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