atlas

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

Parsing Images of Overlapping Organisms With Deep Singling-Out Networks

CVPR 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 15 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 SON-based hypothesis parsing instead of WormToolboxSON fast · LarvaeF1-score: 0.5609 -> 0.8238Helped
Add size-dependent hypothesis penalties (ablation)SON fast · LarvaeF1-score: 0.8238 -> 0.8532Helped
Add size-dependent hypothesis penalties (ablation)SON fair · LarvaeF1-score: 0.8097 -> 0.8329Helped
Add size-dependent hypothesis penalties (ablation)SON hausdorf · LarvaeF1-score: 0.8353 -> 0.8816Helped
Use Hausdorff distance between hypothesis centerlines instead of fast coverage-based distances (ablation)SON image parsing · LarvaeF1-score: 0.8238 -> 0.8353Helped

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