AI Paper Atlas

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

Background-Aware Classification Activation Map for Weakly Supervised Object Localization

Lei Zhu, Qi She, Qian Chen, Xiangxi Meng, Mufeng Geng, Lujia Jin, Yibao Zhang, Qiushi Ren, Yanye Lu

TPAMI 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 37 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 aggregator and background classifier to object-aggregator-only model (ablation)B-CAM · CUB-200 testTop-1 mean: 46.40 -> 49.67Improved
add stagger path (full SSE) to Ours2 (ablation)B-CAM · CUB-200 testTop-1 mean: 49.67 -> 58.43Improved
replace GAP with object aggregator only (ablation)CAM · CUB-200 testTop-1 mean: 46.71 -> 46.40Hurt
use predicted background map as binary mask instead of searched threshold (ablation)B-CAM · CUB-200 testTop-1 mean: 58.43 -> 57.25Hurt
replace CAM with B-CAMCAM · CUB-200 testMBA mean: 62.28 -> 71.79Improved
replace CAM with B-CAMCAM · VOC2012 valpIoU: 46.60 -> 54.43Improved
replace CAM with B-CAM on noisy OpenImagesCAM · OpenImages testpIoU: 42.95 -> 44.31Improved
replace CAM with B-CAM on clean CUB-200 masksCAM · CUB-200 test (clean masks)pIoU: 47.60 -> 57.14Improved
use binary mask Ours-m instead of Ours-p on VOC2012B-CAM · VOC2012 valpIoU: 54.43 -> 54.51Improved
use binary mask Ours-m instead of Ours-p on OpenImagesB-CAM · OpenImages testpIoU: 44.31 -> 42.98Hurt
add B-CAM under optimal image-scale thresholdsCAM · CUB-200 testTop-1 OIS mean: 58.87 -> 70.99Improved
compare one-stage B-CAM against three-stage PSOLPSOL · CUB-200 testTop-1 Loc: 68.17 -> 65.32Hurt

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