AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues

Hengcan Shi, Munawar Hayat, Yicheng Wu, Jianfei Cai

CVPR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 61 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 CLIP-based proposal selection, graph merging, and proposal regressionEdge Boxes proposals · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 42.5 -> 52.1Improved
Use CLIP-based proposal selection, graph merging, and proposal regressionEdge Boxes proposals · COCO validation, 10 proposalsRecall@0.5 (%): 17.1 -> 27.1Improved
Use ProposalCLIP instead of Edge BoxesEdge Boxes proposals · Visual Genome mini, 10 proposalsRecall@0.5 (%): 14.5 -> 24.1Improved
Add CLIP proposal selection (ablation)Edge Boxes on PASCAL VOC 2007 test · PASCAL VOC 2007 testRecall@0.5 (%): 15.2 -> 21.0; 42.5 -> 51.8; 58.3 -> 62.1; 64.7 -> 68.5Improved
Add graph-based proposal merging (ablation)CLIP-selected proposals on PASCAL VOC 2007 test · PASCAL VOC 2007 testRecall@0.5 (%): 21.0 -> 21.6; 51.8 -> 52.4; 62.1 -> 64.6; 68.5 -> 70.8Improved
Add proposal regression (ablation)CLIP selection and graph merging on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 1 proposalRecall@0.5 (%): 21.6 -> 22.1Hurt
Add proposal regression (ablation)CLIP selection and graph merging on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 52.4 -> 52.1Hurt
Add proposal regression (ablation)CLIP selection and graph merging on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 30 proposalsRecall@0.5 (%): 64.6 -> 65.8Improved
Use the initial score alone instead of the final objectness score (ablation)ProposalCLIP on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 51.8 -> 46.5Hurt
Use maximum CLIP similarity instead of the final objectness score (ablation)ProposalCLIP on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 51.8 -> 50.7Hurt
Use CLIP similarity entropy alone instead of the final objectness score (ablation)ProposalCLIP on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 46.5 -> 52.5Improved
Combine entropy, maximum similarity, and the initial score into the final objectness score (ablation)ProposalCLIP on PASCAL VOC 2007 test · PASCAL VOC 2007 test, 10 proposalsRecall@0.5 (%): 52.5 -> 51.8Hurt

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