AI Paper Atlas

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

Learning To Count Everything

CVPR 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 172 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 FamNet instead of MAMLFew-shot counting · FSC-147 testMAE: 24.90 -> 22.08Helped
Use FamNet instead of the strongest detector baseline, Mask R-CNNCounting categories in COCO subsets · Test-COCOMAE: 35.56 -> 22.76Helped
Train FamNet with CARPK data rather than use the FSC-147-pretrained modelFamNet · CARPKMAE: 28.84 -> 18.19Helped
Increase exemplars from 1 to 3 (ablation)FamNet · FSC-147 valMAE: 26.55 -> 23.75Helped
Add multi-scale image features (ablation)FamNet · FSC-147 valMAE: 32.70 -> 27.80Helped
Add multi-scale exemplar features (ablation)FamNet with multi-scale image features · FSC-147 valMAE: 27.80 -> 24.32Helped
Add test-time adaptation (ablation)FamNet with multi-scale image and exemplar features · FSC-147 valMAE: 24.32 -> 23.75Helped

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