AI Paper Atlas

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

Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation

Wei Zhai, Pingyu Wu, Kai Zhu, Yang Hua Cao, Feng Wu, Zheng-Jun Zha

IJCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 42 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 background activation suppression loss L_bas (ablation)FPM baseline · CUB-200-2011GT-known Loc: 71.14 -> 92.15Improved
add L_bas (ablation)FPM baseline · CUB-200-2011Top-1 Loc: 57.89 -> 74.15Improved
add Top-k strategy for final map (ablation)BAS · CUB-200-2011GT-known Loc: 92.15 -> 95.41Improved
add L_bas (ablation)WSSS baseline · PASCAL VOC 2012mIoU: 50.1 -> 57.7Improved
add L_bas (ablation)WSSS baseline · MS COCO 2014mIoU: 32.5 -> 36.9Improved
insert generator after layer 3 instead of layer 1 (ablation)BAS · CUB-200-2011GT-known Loc: 52.87 -> 95.41Improved
insert generator after layer 3 instead of layer 4 (ablation)BAS · CUB-200-2011GT-known Loc: 90.94 -> 95.41Improved
insert generator after layer 3 instead of layer 4 (ablation)BAS · PASCAL VOC 2012mIoU: 55.3 -> 57.7Improved
insert generator after layer 3 instead of layer 4 (ablation)BAS · MS COCO 2014mIoU: 34.8 -> 36.9Improved
remove final ReLU and apply ReLU separately before S and S^b (journal vs conference version)BAS · CUB-200-2011 mean over 4 backbonesGT-known Loc: +0.83Improved
same ReLU changeBAS · ILSVRC mean over 4 backbonesGT-known Loc: +0.11Improved
mask feature maps instead of original image for background map (ablation)BAS · CUB-200-2011localization accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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