AI Paper Atlas

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

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

Lei Zhu, Qian Chen, Lujia Jin, Yunfei You, Yanye Lu

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 25 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
replace CAM with BagCAMs at test timeCAM (ResNet50) · CUB-200G-Loc (%): 66.06 -> 87.44Improved
replace CAM with BagCAMs at test timeCAM (ResNet50) · CUB-200PxAP (%): 65.94 -> 84.38Improved
replace CAM with BagCAMs at test timeHAS (ResNet50) · CUB-200G-Loc (%): 72.55 -> 89.65Improved
replace CAM with BagCAMs at test timeDAOL (ResNet50) · CUB-200PxAP (%): 74.70 -> 90.38Improved
replace CAM with BagCAMs at test timeCAM (ResNet50) · ILSVRCB-Loc (%): 62.69 -> 69.13Improved
replace CAM with BagCAMs at test timeCAM (ResNet50) · OpenImagesPxAP (%): 57.88 -> 62.52Improved
replace CAM with BagCAMs at test timeDAOL (ResNet50) · ILSVRCT-Loc (%): 43.26 -> 44.24No clear effect
use BagCAMs instead of GradCAM++ on intermediate layersCAM (ResNet50) · CUB-200PxAP (%): 76.33 -> 84.38Improved
use BagCAMs instead of PCSDAOL (ResNet50) · CUB-200PxAP (%): 76.81 -> 90.38Improved
select specific localizers per position (Ours3) instead of uniform averaging (Ours1) (ablation)BagCAMs · CUB-200PxAP (%): 77.29 -> 84.38Improved
select specific localizers per position (Ours3) instead of GradCAM++ weighting (Ours2) (ablation)BagCAMs · CUB-200PxAP (%): 81.79 -> 84.38Improved
apply BagCAMs on Res1 features instead of GradCAMResNet CUB-200 · CUB-200PxAP (%): 15.05 -> 71.35Improved

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