AI Paper Atlas

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

Zero-Annotation Object Detection with Web Knowledge Transfer

Qingyi Tao, Hao Yang, Jianfei Cai

ECCV 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 23 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 DA stream alone to web-trained WSD (ablation)WSD baseline VGG_M · VOC 2007 testmAP: 21.5 -> 21.2No clear effect
add DA stream alone to web-trained WSD (ablation)WSD baseline VGG16 · VOC 2007 testmAP: 21.8 -> 21.0Hurt
add one self-training pseudo-label (ST) stream on top of DAWSD+DA VGG_M · VOC 2007 testmAP: 21.2 -> 24.2Improved
add one ST stream on top of DAWSD+DA VGG16 · VOC 2007 testmAP: 21.0 -> 25.0Improved
add second and third chained ST streams (ablation)WSD+DA+ST VGG16 · VOC 2007 testmAP: 25.0 -> 25.4Improved
add second and third chained ST streams (ablation)WSD+DA+ST VGG_M · VOC 2007 testmAP: 24.2 -> 24.6Improved
add DA stream with foreground attention to WSD+3ST (ablation)WSD+3ST VGG_M · VOC 2007 testmAP: 23.5 -> 24.6Improved
add foreground attention to DA stream (ablation)WSD+DA+3ST VGG_M · VOC 2007 testmAP: 23.3 -> 24.6Improved
add DA without foreground attention (ablation)WSD+3ST VGG_M · VOC 2007 testmAP: 23.5 -> 23.3No clear effect
train ST stream simultaneously with WSD instead of isolated pseudo-label training (ablation)WSD+DA+3ST VGG_M · VOC 2007 testmAP: 22.5 -> 24.6Improved
apply full method (DA+3ST) to web-only baselineWSD VGG_M · VOC 2012 testmAP: 17.9 -> 21.7Improved
apply full method (DA+3ST) to web-only baselineWSD VGG16 · VOC 2012 testmAP: 19.2 -> 22.9Improved

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