AI Paper Atlas

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

ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

Vadim Kantorov, Maxime Oquab, Minsu Cho, Ivan Laptev

ECCV 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 297 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 the additive model with the contrastive S model (shared FC layers, frame pooling) (ablation)context-aware WSL · VOC 2007 testmAP: 33.3 -> 36.3Improved
replace the additive model with the contrastive S model (ablation)context-aware WSL · VOC 2007 trainvalCorLoc: 52.8 -> 55.1Improved
add frame pooling (symmetric) to the contrastive model instead of ROI pooling for context (ablation)contrastive model · VOC 2007 testmAP: 32.2 -> 36.3Improved
add frame pooling (symmetric) to the contrastive model instead of ROI pooling for context (ablation)contrastive model · VOC 2007 trainvalCorLoc: 50.2 -> 55.1Improved
add contrastive S context scoring on top of the WSDDN-style baseline (ablation)WSDDN-SSW-S* reimplementation · VOC 2007 testmAP: 30.5 -> 36.3Improved
add contrastive S context scoring on top of the WSDDN-style baseline (ablation)WSDDN-SSW-S* reimplementation · VOC 2007 trainvalCorLoc: 50.0 -> 55.1Improved
add additive context scoring to the WSDDN-style baseline (ablation)WSDDN-SSW-S* reimplementation · VOC 2007 testmAP: 30.5 -> 33.3Improved
add asymmetric contrastive context scoring to the WSDDN-style baseline (ablation)WSDDN-SSW-S* reimplementation · VOC 2007 testmAP: 30.5 -> 32.2Improved
add asymmetric contrastive context scoring to the WSDDN-style baseline (ablation)WSDDN-SSW-S* reimplementation · VOC 2007 trainvalCorLoc: 50.0 -> 50.2No clear effect
train additive and contrastive models jointly by adding their outputs (ablation)context models · VOC 2007 testmAPNo clear effect
add other types of region pooling as input to the localization branch (ablation)context models · VOC 2007 testmAPNo clear effect
share weights or replace context pooling with frame pooling in the additive model (ablation)additive model · VOC 2007 testmAPHurt

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