AI Paper Atlas

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

Progressive Representation Adaptation for Weakly Supervised Object Localization

Dong Li, Jia‐Bin Huang, Yali Li, Shengjin Wang, Ming–Hsuan Yang

TPAMI 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 17 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 MIL selection to class-specific proposals (ablation)class-specific proposals · VOC 2007 trainvalCorLoc: 31.8 -> 41.2Improved
add detection network fine-tuning (ablation)CS+MIL · VOC 2007 trainvalCorLoc: 41.2 -> 49.8 (AlexNet), 52.4 (VGGNet)Improved
add activation scores (ablation)CS+MIL+FT (VGGNet) · VOC 2007 trainvalCorLoc: 52.4 -> 54.5Improved
add segmentation cues for box refinement (ablation)CS+AS+MIL+FT · VOC 2007 trainvalCorLoc: 54.5 -> 59.0Improved
train detector on MIL-selected proposals directly (no classification adaptation) (ablation)MIL baseline (AlexNet) · VOC 2007 testmAP: 22.7 -> 23.0No clear effect
add class-specific proposal mining from adapted classifier (ablation)MIL+FT (AlexNet) · VOC 2007 testmAP: 23.0 -> 31.0Improved
add class-specific proposal mining from adapted classifier (ablation)MIL+FT (VGGNet) · VOC 2007 testmAP: 26.2 -> 39.5Improved
add MIL step to class-specific proposals (ablation)CS+FT (AlexNet / VGGNet) · VOC 2007 testmAP: 19.5 -> 31.0 (AlexNet), 20.5 -> 39.5 (VGGNet)Improved
add activation scores (ablation)CS+MIL+FT (VGGNet) · VOC 2007 testmAP: 39.5 -> 41.2Improved
add proposal refinement with segmentation (ablation)CS+AS+MIL+FT (VGGNet) · VOC 2007 testmAP: 41.2 -> 42.5Improved
use VGGNet instead of AlexNetCS+MIL+FT · VOC 2007 testmAP: 31.0 -> 39.5Improved
use In-Out mask-out instead of Whole-Out (ablation)proposal mining · VOC 2007 train/valCorLoc@M: 64.9 -> 73.8 (M=10)Improved

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