AI Paper Atlas

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

EA-KD: Entropy-based Adaptive Knowledge Distillation

Chi-Ping Su, Ching-Hsun Tseng, Bin Pu, Lei Zhao, Jiewen Yang, Zhuangzhuang Chen, Shin-Jye Lee

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 16 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 entropy-based reweighting w_EA to KD lossKD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.33 -> 75.46Improved
add teacher-entropy weight w_base (ablation)KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.33 -> 75.14Improved
add interaction weight w_interact only (ablation)KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.33 -> 74.76Improved
combine w_base and w_interact into w_EA (ablation)KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 75.14 -> 75.46Improved
invert teacher-entropy weighting (low entropy gets high weight) (ablation)KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.33 -> 72.73Hurt
invert student-entropy weighting (ablation)KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.33 -> 68.90Hurt
set entropy temperature T' to 3 instead of 2 (ablation)EA-KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 73.90 -> 75.46Improved
set entropy temperature T' to 3 instead of 4 (ablation)EA-KD · CIFAR-100 (ResNet32x4->ResNet8x4)accuracy: 75.22 -> 75.46Improved
add EA reweighting to MLD+LSMLD+LS · CIFAR-100 (VGG13->MN-V2)accuracy: 70.94 -> 70.67Hurt
add EA reweighting to FCFDFCFD · CIFAR-100 (WRN-40-2->WRN-40-1)accuracy: 75.46 -> 75.30Hurt
add EA reweighting to DKDDKD · CIFAR-100 (beta sweep)accuracy variance over beta: 0.31 -> 0.10Improved
add EA reweighting to KD with DeiT-B teacherKD · Tiny-ImageNet (DeiT-B to ResNet8x4)accuracy: 56.30 -> 58.36Improved

Later papers that compared with this method

1 later accepted paper reports EA-KD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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