AI Paper Atlas

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

Sparse-Shot Learning With Exclusive Cross-Entropy for Extremely Many Localisations

Andreas Panteli, Jonas Teuwen, Hugo Horlings, Efstratios Gavves

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 3 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
replace cross-entropy by exclusive cross-entropyYOLLO · TNBC detection (30% annotations)F1: 0.65 -> 0.70Improved
replace cross-entropy by exclusive cross-entropyYOLLO · TNBC detection (60% annotations)F1: 0.7 -> 0.75Improved
add focal reweighing on unannotated terms of exclusive cross-entropy (ablation)Exclusive cross-entropy · TNBC detection (30% annotations)F1: 0.70 -> 0.74Improved
add focal reweighing on unannotated terms of exclusive cross-entropy (ablation)Exclusive cross-entropy · TNBC detection (60% annotations)F1: 0.75 -> 0.80Improved
add focal loss to standard cross-entropy (ablation)Cross-entropy · TNBC detection (30% annotations)F1: 0.65 -> 0.36Hurt
add focal loss to standard cross-entropy (ablation)Cross-entropy · TNBC detection (60% annotations)F1: 0.7 -> 0.49Hurt
add weak supervision pseudo-labels (tau 0.75) (ablation)Cross-entropy · TNBC detection (30% annotations)F1: 0.65 -> 0.64No clear effect
add weak supervision pseudo-labels (tau 0.50) (ablation)Cross-entropy · TNBC detection (60% annotations)F1: 0.7 -> 0.64Hurt
use sigmoid annealing of rho instead of fixed rho 0.75 (ablation)Exclusive cross-entropy + focal loss · TNBC detection (30% annotations)F1: 0.68 -> 0.74Improved
use sigmoid annealing instead of linear annealing (ablation)Exclusive cross-entropy + focal loss · TNBC detection (60% annotations)F1: 0.73 -> 0.80Improved
use exclusive cross-entropy instead of cross-entropyUnet · Segmentation on nine datasets with sparse annotationsDICE: up to 85%Improved
use exclusive cross-entropy instead of cross-entropyYOLLO · TIL localisationexclusive recall: 0.85 -> 0.88Improved

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