AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Variational Patch Gating for Training-Free Few-Shot Classification

Ahmed Radwan, Ahmad Abdel-Qader, Islam Osman, Mohamed Shehata

ECCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 0 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
add global CLS branch to local evidence (ablation)VPG · CDFSL 5-way 5-shot (avg)accuracy: 65.16 -> 67.55Improved
add local patch evidence branch to global prototype (ablation)VPG · CDFSL 5-way 5-shot (avg)accuracy: 66.21 -> 67.55Improved
use softplus bounded evidence instead of raw negative soft-min cost (ablation)VPG · CDFSL 5-way 5-shot (avg)accuracy: 66.74 -> 67.55Improved
add episodic fine-tuning of last blockVPG · CDFSL 5-way 5-shot (avg)accuracy: 67.55 -> 71.06Improved
add episodic fine-tuning of last blockVPG · HEp 5-shotaccuracy: 69.26 -> 76.35Improved
add episodic fine-tuning of last blockVPG · BCCD_WBC 5-shotaccuracy: 68.86 -> 80.30Improved
vary foreground prior pi from 0.1 to 0.9 (ablation)VPG · CDFSL 5-way 5-shotaccuracy: less than 1%No clear effect
vary temperature epsilon from 0.01 to 0.1 (ablation)VPG · CDFSL 5-way 5-shotaccuracy: less than 1%No clear effect
reduce epsilon to 0.005 (ablation)VPG · CDFSL EuroSATaccuracyHurt
use parts-only (alpha=0) mixing instead of 0.4-0.6 (ablation)VPG · CDFSL EuroSAT and CropDiseasesaccuracy: loses ~2%Hurt
replace H-OT with VPG (training-free) on miniImageNet 5-shot (ablation)VPG · miniImageNet 5-way 5-shotaccuracy: 93.91 -> 96.06Improved
replace H-OT with VPG (training-free) on CUB 1-shotVPG · CUB 5-way 1-shotaccuracy: 87.64 -> 86.02Hurt

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