AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Post-training Feature Pruning for Fundus Images Classification

Van-Nguyen Pham, Duc-Tai Le, Junghyun Bum, Hyunseung Choo

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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
apply GFP post-training feature pruning to CoAtNetCoAtNet-2 · DDRAUROC: 95.17 -> 96.73Improved
apply GFP to CoAtNetCoAtNet-2 · PAPILAAUPRC: 80.70 -> 84.43Improved
apply GFP to EfficientNetV2EfficientNetV2-m · RETINAAUROC: 77.85 -> 79.10Improved
apply GFP to EfficientNetV2EfficientNetV2-m · PAPILAAUROC: 81.33 -> 81.21No clear effect
apply GFP to ViTViT · PAPILAAUPRC: 79.27 -> 77.43Hurt
apply GFP to ViTViT · Messidor-2AUROC: 85.29 -> 85.36No clear effect
use magnitude pruning (MP) instead of GFP on EfficientNetV2EfficientNetV2-m · RETINAAUROC: 77.85 -> 73.57Hurt
use L1 regularization feature selection on CoAtNetCoAtNet-2 · DDRAUROC: 95.17 -> 91.33Hurt
token pruning (TRAM, LTMP) instead of feature pruning on ViTViT · RETINAAUROC: 90.75 -> 83.17Hurt
apply GFP to CoAtNet (feature compactness)CoAtNet-2 · PAPILAintra-class variance: 196.04 -> 8.41Improved
apply GFP to EfficientNetV2 for cross-dataset transferEfficientNetV2-m · Messidor-2 to DDRAUROC: 80.83 -> 82.99Improved
apply GFP to EfficientNetV2 for cross-dataset transferEfficientNetV2-m · DDR to Messidor-2AUROC: 77.38 -> 77.17No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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