AI Paper Atlas

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

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Bowen Dong, Zitong Huang, Yuelin Guo, Qilong Wang, Zhenxing Niu, Wangmeng Zuo

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 57 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
use R50-C4 backbone for the adjuster instead of VGG-16 (ablation)LBBA with WSDDN · VOC 2007mAP / CorLoc: 50.2 -> 52.7 mAP; 67.7 -> 70.3 CorLocImproved
add LBBA to WSDDN (ablation)WSDDN · VOC 2007mAP: 46.6 -> 52.7Improved
add LBBA to OICR+REG (ablation)OICR · VOC 2007mAP: 48.6 -> 55.1Improved
add LBBA to OICR+REG with top-p% pseudo-label mining (ablation)OICR+ · VOC 2007mAP: 51.4 -> 55.8Improved
add LBBA to WSDDN (ablation)WSDDN · VOC 2007CorLoc: 64.7 -> 70.3Improved
add LBBA to OICR+REG with top-p% pseudo-label mining (ablation)OICR+ · VOC 2007CorLoc: 64.9 -> 71.6Improved
increase multi-stage iterations T from 0 to 3 (ablation)LBBA with OICR+ · VOC 2007mAP: 53.1 -> 55.8Improved
increase multi-stage iterations T from 0 to 3 (ablation)LBBA adjuster · COCO-60adjuster mAP: 29.1 -> 30.9Improved
increase T beyond 2 (ablation)LBBA with OICR+ · VOC 2007mAP: 55.7 -> 55.8No clear effect
use learnable auxiliary WSOD network instead of MCG proposals (ablation)LBBA · VOC 2007mAP: 54.3 -> 55.8Improved
use learnable auxiliary WSOD network instead of MCG proposals (ablation)LBBA adjuster · COCO-60adjuster mAP: 29.6 -> 30.9Improved
add classification score masking strategy (ablation)LBBA · COCO-20mAP: 13.0 -> 13.7Improved

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