AI Paper Atlas

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

How to Train the Teacher Model for Effective Knowledge Distillation

Shayan Mohajer Hamidi, Xizhen Deng, Renhao Tan, Linfeng Ye, Ahmed Hussein Salamah

ECCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 13 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
train the teacher with MSE loss instead of cross-entropy (ablation)KD methods (AT, PKT, SP, CC, RKD, VID, CRD, REVIEW, DKD, HSAKD) · CIFAR-100student top-1 accuracy: up to +2.67Improved
train the teacher with MSE loss instead of cross-entropy (ablation)KD, REVIEW+KD · ImageNet (ResNet34-ResNet18)student top-1 accuracy: 71.03 -> 71.58 (KD)Improved
train the teacher with MSE loss instead of cross-entropy (ablation)teacher network · CIFAR-100 and ImageNetteacher accuracy: 79.34 -> 74.54 (ResNet-50 CIFAR-100)Hurt
train the teacher with MSE loss with feature-based methods combined with KD (ablation)AT+KD, PKT+KD, etc. · CIFAR-100student top-1 accuracy: +2.24 (AT+KD, ResNet-32x4 -> ShuffleNetV2)Improved
train the teacher with MSE loss for CC+KD (ablation)CC+KD · CIFAR-100 (ResNet-50 -> VGG-8)student top-1 accuracy: 73.48 -> 70.79Hurt
use MSE teacher in different-architecture teacher-student pairs (ablation)KD methods · CIFAR-100student top-1 accuracyImproved
train the teacher with MSE loss in binary classification KD (ablation)KD, AT, CC, VID · binary CIFAR variantsstudent accuracy: 71.40 -> 71.23 (KD, CIFAR-50-74)Mixed
use MSE teacher in semi-supervised distillation (ablation)ResNet18 student · CIFAR-10 with 1-8% labelsstudent 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