AI Paper Atlas

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

Zero-Shot Object Counting

Jingyi Xu, Hieu Le, Vu Nguyen, Viresh Ranjan, Dimitris Samaras

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 67 citations (OpenAlex)

Read the paper

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 class-name-guided patch selection instead of RPN exemplarsExemplar-free counting on FSC-147 · FSC-147 testRMSE: 14.52Improved
Add class-prototype filtering to random patch selection (ablation)Ours (Base) · FSC-147 valMAE: 35.20 -> 28.01Improved
Add class-prototype filtering to random patch selection (ablation)Ours (Base) · FSC-147 testMAE: 31.37 -> 25.30Improved
Add error-predictor exemplar selection to random patch selection (ablation)Ours (Base) · FSC-147 valMAE: 35.20 -> 27.98Improved
Add error-predictor exemplar selection to random patch selection (ablation)Ours (Base) · FSC-147 testMAE: 31.37 -> 23.80Improved
Combine class-prototype filtering with error-predictor selection (ablation)Ours (Base) · FSC-147 valMAE: 35.20 -> 26.93Improved
Combine class-prototype filtering with error-predictor selection (ablation)Ours (Base) · FSC-147 testMAE: 31.37 -> 22.09Improved
Use prototype-selected patches instead of random patches as exemplarsFamNet · FSC-147 valMAE: 5.18Improved
Use prototype-selected patches instead of random patches as exemplarsBMNet · FSC-147 valMAE: 8.59Improved
Use prototype-selected patches instead of random patches as exemplarsBMNet+ · FSC-147 valMAE: 5.60Improved
Add error-predictor selection after prototype filteringFamNet · FSC-147 valMAE: 1.76Improved
Add error-predictor selection after prototype filteringBMNet · FSC-147 valMAE: 1.00Improved

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