AI Paper Atlas

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

Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation

Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang

ICCV 2021 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 136 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 1x1 linear transformation layer on student feature (ablation)ICKD-C · CIFAR-100 test (ResNet110 to ResNet20)top-1 accuracy: 70.96 -> 71.68Improved
add 1x1 linear transformation layer on student feature (ablation)ICKD-C · CIFAR-100 test (VGG13 to VGG8)top-1 accuracy: 73.85 -> 73.42Hurt
add 1x1 linear transformation layer on student feature (ablation)ICKD-C · CIFAR-100 test (ResNet110 to ResNet32)top-1 accuracy: 73.90 -> 73.89No clear effect
add 1x1 linear transformation layer on student feature (ablation)ICKD-C · CIFAR-100 test (ResNet32x4 to ResNet8x4)top-1 accuracy: 74.40 -> 75.25Improved
add KL loss to ICC loss (ablation)ICKD-C · CIFAR-100 test (WRN-40-2 to WRN-40-1)top-1 accuracy: 74.33 -> 74.63Improved
add KL loss to ICC loss (ablation)ICKD-C · CIFAR-100 test (WRN-40-2 to WRN-16-2)top-1 accuracy: 75.64 -> 75.57No clear effect
distill ICC at stage 4 only versus stage 1 only (ablation)ICKD-C · ImageNet (ResNet34 to ResNet18)top-1 accuracy: 70.49 -> 72.16Improved
add ICC transfer at stages 3 and 4 instead of stage 4 only (ablation)ICKD-C · ImageNet (ResNet34 to ResNet18)top-1 accuracy: 72.16 -> 72.33Improved
use Gaussian kernel instead of the inner-product ICC (L2) form (ablation)ICKD-C · ImageNet (ResNet34 to ResNet18)top-1 accuracy: 72.16 -> 70.63Hurt
use smooth L1 loss instead of L2 (ablation)ICKD-C · ImageNet (ResNet34 to ResNet18)top-1 accuracy: 72.16 -> 72.29No clear effect
partition the feature map into 32x32 grid for ICC (ablation)ICKD-S · Pascal VOC val (ResNet18 student)mIoU: 74.14 -> 75.01Improved
partition the feature map into 16x16 grid instead of 32x32 (ablation)ICKD-S · Pascal VOC val (MobileNetV2 student)mIoU: 72.58 -> 72.79Improved

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