AI Paper Atlas

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

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

Jungbeom Lee, Eunji Kim, Jisoo Mok, Sungroh Yoon

TPAMI 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 46 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 adversarial climbing (ablation)CutMix · CUB-200-2011Top-1 Loc: 57.6 -> 62.5Improved
add regularization on top of adversarial climbing (ablation)CutMix + adversarial climbing · CUB-200-2011Top-1 Loc: 62.5 -> 64.9Improved
add regularization (lambda=7 vs 0) (ablation)AdvCAM · PASCAL VOC 2012 trainseed mIoU: 50.43 -> 55.55Improved
aggregate CAMs over all iterations instead of last iteration (ablation)AdvCAM · PASCAL VOC 2012 trainseed mIoU: 54.0 -> 55.6Improved
add adversarial climbing (ablation)Grad-CAM++ · PASCAL VOC 2012 trainseed mIoU: 47.7 -> 50.7Improved
add adversarial climbing (ablation)Chang et al. · PASCAL VOC 2012 trainseed mIoU: 50.9 -> 53.7Improved
add adversarial climbing (ablation)SEAM · PASCAL VOC 2012 trainseed mIoU: 55.4 -> 58.6Improved
add adversarial climbing (ablation)IRN · PASCAL VOC 2012 trainseed mIoU: 48.8 -> 55.6Improved
add salient object detector (ablation)AdvCAM · PASCAL VOC 2012 trainseed mIoU: 55.6 -> 60.8Improved
add CRF post-processingAdvCAM · PASCAL VOC 2012 trainseed mIoU: 55.6 -> 62.1Improved
vary masking threshold tau from 0.3 to 0.7 (ablation)AdvCAM · PASCAL VOC 2012 trainseed mIoUNo clear effect
apply adversarial climbing to small-object classes (ablation)AdvCAM vs CAM · MS COCO 2014 smallest 10 classesrecall: 73.0 -> 64.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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