AI Paper Atlas

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

Personalized Education: Blind Knowledge Distillation

Xiang Deng, Jian Zheng, Zhongfei Zhang

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 5 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
use MixPatch instead of Mixup for distillation samples (ablation)KD · CIFAR-100 (WRN-40-2 -> WRN-16-2)test accuracy (%): 75.56 -> 75.94Improved
use MixPatch instead of Mixup for distillation samples (ablation)KD · CIFAR-100 (VGG-13 -> VGG-8)test accuracy (%): 74.58 -> 74.93Improved
add adaptive BKR search over MixPatch parameters (ablation)KD+MixPatch · CIFAR-100 (WRN-40-2 -> WRN-16-2)test accuracy (%): 75.94 -> 76.57Improved
add adaptive BKR search over MixPatch parameters (ablation)KD+MixPatch · CIFAR-100 (VGG-13 -> VGG-8)test accuracy (%): 74.93 -> 75.41Improved
add Personalized Education to KDKD · CIFAR-100 (ResNet32x4 -> ShuffleNetV2)test accuracy (%): 74.45 -> 79.83Improved
add Personalized Education to KDKD · CIFAR-100 (ResNet32x4 -> ResNet8x4)teacher-student accuracy gap: 6.30 -> 3.36Improved
add Personalized Education to KDKD · Tiny ImageNet (VGG-13 -> VGG-8)top-1 accuracy (%): 60.19 -> 62.40Improved
replace PE by GAN-generated distillation data (GANKD)KD · CIFAR-100 (ResNet-110 -> ResNet-32)test accuracy (%): 73.08 -> 72.87Hurt
add PE to AB distillationAB · CIFAR-100 (WRN-40-2 -> WRN-16-2)test accuracy (%): 68.89 -> 72.20Improved
add PE to CRD distillationCRD · CIFAR-100 (WRN-40-2 -> WRN-16-2)test accuracy (%): 76.04 -> 76.81Improved
distill on simulated full data distribution instead of training pointsKD · CIFAR-100 (ResNet32x4 -> ShuffleNetV2)test accuracy (%): 74.45 -> 81.64Improved
distill on simulated data distribution for incapable student SN2KD · CIFAR-100 (VGG-13 -> SN2)test accuracy (%): 26.04 -> 25.58No clear effect

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