AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Forget Me Not: Fighting Local Overfitting With Knowledge Fusion and Distillation

Uri Stern, Eli Corn, Daphna Weinshall

TPAMI 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 1 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
apply Knowledge Fusion of mid-training checkpointsResNet18 · CIFAR-100 (clean)accuracy: 78.85 -> 79.36Improved
apply Knowledge Fusion of mid-training checkpointsResNet18 · TinyImageNet (clean)accuracy: 65.30 -> 68.33Improved
distill the KF ensemble into a single student (ablation)KF ensemble · CIFAR-100 (clean)accuracy: 79.36 -> 80.29Improved
distill the KF ensemble into a single student (ablation)KF ensemble · TinyImageNet (clean)accuracy: 68.33 -> 69.96Improved
distill into a student instead of averaging checkpoint weights (ablation)KF · CIFAR-100 (clean)accuracy: 78.48 -> 80.29Improved
apply KF under heavy label noiseResNet18 · CIFAR-100 (40% asym noise)accuracy: 49.95 -> 63.37Improved
distill the KF ensemble (ablation)KF ensemble · CIFAR-100N (40% noise)accuracy: 63 -> 64.12Improved
distill the independent ensemble (ablation)independent ensemble · CIFAR-100 (clean)accuracy: 82.13 -> 79.93Hurt
distill the independent ensemble (ablation)independent ensemble · CIFAR-100 (40% asym noise)accuracy: 55.18 -> 56.84Improved
replace horizontal ensemble with KFResNet18 · CIFAR-100 (clean)accuracy: 78.42 -> 79.36Improved
apply KF to a ViT-B/16ViT-B/16 · ImageNetaccuracy: 79.16 -> 80.34Improved
apply KF on head-only finetuning of pretrained modelResNet18 · CIFAR-100 (transfer)accuracy: 61.7 -> 65.24Improved

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