AI Paper Atlas

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

Towards Precise End-to-End Weakly Supervised Object Detection Network

Ke Yang, Dongsheng Li, Yong Dou

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 141 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 guided attention module (GAM) to the MIL detector (ablation)MIL detector (OICR) · VOC 2007 testmAP: 41.3 -> 43.3Improved
add GAM to the MIL detector (ablation)MIL detector (OICR) · VOC 2007 trainvalCorLoc: 60.6 -> 61.4Improved
train regression branch jointly instead of a separate Fast R-CNN phase (ablation)MIL detector · VOC 2007 testmAP: 45.9 -> 47.3Improved
train regression branch jointly instead of a separate Fast R-CNN phase (ablation)MIL detector · VOC 2007 trainvalCorLoc: 64.5 -> 65.8Improved
add GAM on top of joint regression (ablation)MIL+REG · VOC 2007 testmAP: 47.3 -> 48.6Improved
add GAM on top of joint regression (ablation)MIL+REG · VOC 2007 trainvalCorLoc: 65.8 -> 66.8Improved
add joint regression branch to MIL detector (ablation)MIL detector · VOC 2007 testmAP: 41.3 -> 47.3Improved
add separate Fast R-CNN second phase to MIL detector (ablation)MIL detector · VOC 2007 testmAP: 41.3 -> 45.9Improved
use PCL instead of OICR as the MIL base with GAM+REGMIL+GAM+REG · VOC 2007 testmAP: 48.6 -> 51.5Improved
use PCL instead of OICR as the MIL base with GAM+REGMIL+GAM+REG · VOC 2012 testmAP: 46.8 -> 45.6Hurt
single joint model versus OICR ensemble with Fast R-CNNOICR · VOC 2007 testmAP: 47.0% mAP Versus 48.6% mAPImproved
single joint model versus OICR ensemble with Fast R-CNNOICR · VOC 2007 trainvalCorLoc: 60.6% CorLoc Versus 66.8% CorLocImproved

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