AI Paper Atlas

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

Factorizing Knowledge in Neural Networks

Xingyi Yang, Jingwen Ye, Xinchao Wang

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 120 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
factorize teacher into CKN plus task-specific network (KF) instead of baseline MBNv2MBNv2 · CIFAR-10accuracy: 93.58 -> 94.80Improved
use KF (ResNet-18 CKN + MBNv2x0.5 TSN) instead of WRN-28-10 baselineWRN-28-10 · CIFAR-10accuracy: 95.32 -> 95.40Improved
use KF (WRN-28-2 CKN + 2 TSN) instead of ResNet-18 baselineResNet-18 · CIFAR-10accuracy: 94.45 -> 95.03Improved
add knowledge distillation to MBNv2 on CIFAR-10 sub-tasksMBNv2 · CIFAR-10 binary and trinary sub-tasksaccuracy: +2%Improved
replace distillation with knowledge factorization on sub-tasksMBNv2 · CIFAR-10 binary and trinary sub-tasksaccuracy: +1%Improved
use factor networks instead of KD/baseline under adversarial attackMBNv2, ResNet-18 · CIFAR-10 FGSM and PGD-40robust 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