AI Paper Atlas

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

Relation-aware Instance Refinement for Weakly Supervised Visual Grounding

Yongfei Liu, Bo Wan, Lin Ma, Xuming He

CVPR 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 53 citations (OpenAlex)

Check 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 relation-aware instance refinement rather than Contrastive LearningWeakly supervised visual grounding · Flickr30K EntitiesAcc: 51.67 -> 59.27Improved
Use relation-aware instance refinement rather than Contrastive LearningWeakly supervised visual grounding · Flickr30K EntitiesPointIt: 76.74 -> 78.60Improved
Use relation-aware instance refinement rather than KPRNWeakly supervised visual grounding · ReferItGameAcc: 33.87 -> 37.68Improved
Use relation-aware instance refinement rather than KAC Net*Weakly supervised visual grounding · ReferItGamePointIt: 56.57 -> 58.96Improved
Add two-stage denoising (ablation)Weakly supervised visual grounding baseline · Flickr30K Entities valAcc: 48.18 -> 50.80Improved
Add self-taught regression with phrase features (ablation)TSD grounding model · Flickr30K Entities valAcc: 50.80 -> 56.88Improved
Include the noun phrase feature in proposal-offset estimation (ablation)TSD + STR grounding model · Flickr30K Entities valAcc: 54.05 -> 56.88Improved
Add visual object graph network and relation constraint (ablation)TSD + STR grounding model · Flickr30K Entities valAcc: 56.88 -> 58.30Improved
Use learned graph attention instead of uniform graph weights (ablation)TSD + STR + VOGN + RC model · Flickr30K Entities valAcc: 55.60 -> 58.30Improved
Remove self-taught regression loss (ablation)Relation-aware Instance Refinement · Flickr30K Entities valAccHurt
Set retained proposals per phrase K to 3 instead of 5 (ablation)Relation-aware Instance Refinement · Flickr30K Entities valAcc: 58.30 -> 57.47Hurt
Set retained proposals per phrase K to 10 instead of 5 (ablation)Relation-aware Instance Refinement · Flickr30K Entities valAcc: 58.30 -> 57.15Hurt

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