AI Paper Atlas

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

Local Correlation Consistency for Knowledge Distillation

Xiaojie Li, Jianlong Wu, Hongyu Fang, Yue Liao, Fei Wang, Chen Qian

ECCV 2020 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 55 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 intra-patch local correlation loss to KD (ablation)KD, ResNet14/ResNet20 students · CIFAR100top-1 accuracy: 69.78 -> 70.00 (ResNet14); 71.47 -> 72.04 (ResNet20)Improved
add inter-same local correlation loss to KD (ablation)KD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 69.78 -> 70.20; 71.47 -> 71.96Improved
add inter-diff local correlation loss to KD (ablation)KD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 69.78 -> 70.03; 71.47 -> 72.10Improved
combine all three local losses (ablation)KD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 69.78 -> 70.37; 71.47 -> 72.31Improved
add class-aware attention module (CAAT) (ablation)local-loss KD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 70.37 -> 70.48; 72.31 -> 72.63Improved
increase patch grid k from 1 to 4 (ablation)local correlation loss, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 69.98 -> 70.37; 71.82 -> 72.31Improved
use CAAT instead of AT attention (ablation)LKD, ResNet14 · CIFAR100top-1 accuracy: 69.88 -> 70.48Improved
use CAAT instead of Grad-CAM attention (ablation)LKD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 70.41 -> 70.48; 72.18 -> 72.63Improved
use AT activation attention instead of no attention (ablation)LKD, ResNet14/ResNet20 · CIFAR100top-1 accuracy: 70.37 -> 69.88; 72.31 -> 72.34Mixed
replace global correlation (SP, CC) with local correlation (LKD)KD students · CIFAR100top-1 accuracy: 69.77 -> 70.48 (ResNet14, CC vs LKD)Improved
replace KD with LKDResNet18 student · ImageNettop-1 accuracy: 71.34 -> 71.54Improved
replace CC with LKDResNet18 student · ImageNettop-5 accuracy: 90.26 -> 90.30Improved

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