AI Paper Atlas

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

What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs

Tal Shaharabany, Yoad Tewel, Lior Wolf

NeurIPS 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 9 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
Use the proposed weakly supervised localization network instead of the strongest listed baselineCUB with VGG16 · CUB-200-2011localization accuracy: 91.07 -> 93.94Improved
Use the proposed network instead of FGStanford-Cars · Stanford-Carslocalization accuracy: 96.2 -> 98.9Improved
Use the proposed network instead of FGStanford-Dogs · Stanford-Dogslocalization accuracy: 79.2 -> 86.4Improved
Use the proposed phrase-grounding network instead of GAEVG-trained phrase grounding on VG · VGpointing game accuracy: 54.72 -> 62.31Improved
Use Selective Search proposals and the complete WWbL inference method instead of GAE heatmapsWWbL · Flickr30K, MS-COCO trainedpoint accuracy: 56.25 -> 61.38Improved
Add the CLIP relevancy-map loss to the other three losses (ablation)WSOL network on CUB · CUBlocalization accuracy: 90.02 -> 96.54Improved
Add regularization to the relevancy-map, foreground, and background losses (ablation)WSOL network on CUB · CUBlocalization accuracy: 91.08 -> 96.54Improved
Add background loss to the relevancy-map, foreground, and regularization losses (ablation)WSOL network on CUB · CUBlocalization accuracy: 94.73 -> 96.54Improved
Add foreground loss to the relevancy-map, background, and regularization losses (ablation)WSOL network on CUB · CUBlocalization accuracy: 92.67 -> 96.54Improved
Train with only the CLIP relevancy-map loss, removing the other losses (ablation)WSOL network on CUB · CUBlocalization accuracy: 96.54 -> 87.02Hurt
Set the relevancy-map loss weight lambda3 to 4 rather than 0 (ablation)WSOL network on CUB · CUBlocalization accuracy: 90.02 -> 96.50Improved
Replace Selective Search with iterative region removal (ablation)WWbL inference · VG, VG trainedpointing game accuracy: 43.91 -> 35.02Hurt

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