AI Paper Atlas

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

Towards Zero-Shot Diabetic Retinopathy Grading: Learning Generalized Knowledge via Prompt-Driven Matching and Emulating

Huan Wang, Haoran Li, Yuxin Lin, Huaming Chen, Jun Yan, Lijuan Wang, Jiahua Shi, Qihao Xu, Yongting Hu, Yong Xu, Jun Shen

AAAI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 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
two-stage prompt matching then emulating (ProME-DR) instead of fully fine-tuned SigLIPSigLIP-B/16 · Seen-to-Unseen DR grades, 8-dataset average (16-shot)HM accuracy: 67.69 -> 71.81Improved
ProME-DR vs prompt-tuning baselines on unseen classesMMRL · Seen-to-Unseen DR grades, 8-dataset average (16-shot)unseen-class accuracy: 39.37 -> 68.04Improved
prompt tuning (VPT) instead of fully fine-tuned CLIPCLIP-B/32 · Seen-to-Unseen DR grades, 8-dataset average (16-shot)HM accuracy: 65.64 -> 50.72Hurt
most prompt-based baselines versus fully fine-tuned CLIP on unseen classesprompt tuning (e.g. MMRL) · Seen-to-Unseen DR grades, 8-dataset average (16-shot)unseen-class accuracy: 47.31 -> 39.37Hurt
train on MFIDDR and test directly on 7 other datasets using ProME-DRSigLIP-B/16 · Cross-dataset generalizationaccuracy: 55.97 -> 64.16Improved
ProME-DR vs SMVDR supervised on MFIDDRSMVDR · MFIDDR supervisedaccuracy: 81.64 -> 87.90Improved
ProME-DR vs SMVDR on specificitySMVDR · MFIDDR supervisedspecificity: 89.92 -> 85.29Hurt
add contrastive loss Lcl (lambda2 > 0) and distillation loss Ldis (lambda1 > 0) (ablation)ProME-DR · Seen-to-Unseen DR gradesHM accuracyImproved
increase temperature tau toward 0.06 (ablation)ProME-DR · Seen-to-Unseen DR gradesHM accuracyImproved

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