AI Paper Atlas

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

Knowledge Condensation Distillation

Chenxin Li, Mingbao Lin, Zhiyuan Ding, Nie Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Liujuan Cao

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 46 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 OGVE ranking instead of random selection of knowledge points (ablation)KCD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 74.54 -> 75.48Improved
add online value recording (ablation)KCD OGVE · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.01 -> 75.48Improved
add cost-aware ranking (ablation)KCD OGVE · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.27 -> 75.48Improved
add VAKS on top of OGVE (ablation)KCD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.48 -> 75.70Improved
use adaptive perturbation ratio instead of fixed eps_m (ablation)VAKS · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.57 -> 75.70Improved
add knowledge augmentation on the boundary set (ablation)KCD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.45 -> 75.70Improved
augment low-value K1L rather than high-value K1H (ablation)VAKS · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.52 -> 75.70Improved
condense to rho=0.7 rather than 0.3 (ablation)KCD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 74.07 -> 75.70Improved
condense to rho=0.7 rather than 0.9 (ablation)KCD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 75.01 -> 75.70Improved
set alpha=0.03 rather than 0.01 (ablation)KCD · CIFAR100 VGG13 -> MobileNetV2accuracy: 66.40 -> 68.61Improved
add knowledge condensation to KDKD · CIFAR100 WRN-40-2 -> WRN-16-2accuracy: 74.92 -> 75.70Improved
add knowledge condensation to KDKD · ImageNet ResNet34 -> ResNet18top-1 error: 29.34 -> 28.61Improved

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