AI Paper Atlas

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

Correlation Congruence for Knowledge Distillation

Baoyun Peng, Xiao Jin, Jiaheng Liu, Dongsheng Li, Yichao Wu, Yu Liu, Shunfeng Zhou, Zhaoning Zhang

ICCV 2019 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 629 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 correlation congruence to instance-level KD (ablation)KD · CIFAR-100 (ResNet-20)top-1 accuracy: 70.8 -> 72.4Improved
add correlation congruence to instance-level KD (ablation)KD · CIFAR-100 (ResNet-14)top-1 accuracy: 68.3 -> 70.2Improved
add correlation congruence to instance-level KD (ablation)KD · ImageNet-1K (MobileNetV2 0.5x)top-1 accuracy: 66.7 -> 67.7Improved
add correlation congruence to instance-level KD (ablation)KD · MSMT17 (ResNet-18)rank-1 / mAP: 56.8 -> 59.7 rank-1; 28.3 -> 30.7 mAPImproved
add correlation congruence to L2-mimic loss (ablation)L2 mimic · MegaFace (1M distractors)rank-1 identification rate: 83.01 -> 86.29Improved
use Gaussian RBF instead of MMD as the correlation metric (ablation)CCKD · MSMT17mAP: 29.4 -> 30.4Improved
use Gaussian RBF instead of Bilinear Pool as the correlation metric (ablation)CCKD · MSMT17mAP: 30.2 -> 30.4Improved
raise Taylor expansion order of Gaussian RBF from 1 to 3 (ablation)CCKD · MSMT17rank-1 / mAP: 59.2 -> 60.5 rank-1; 30.1 -> 30.7 mAPImproved
use CUR-sampler (k=4) instead of uniform random sampler (ablation)CCKD · MSMT17rank-1 / mAP: 57.2 -> 59.7 rank-1; 28.6 -> 30.2 mAPImproved
use SUR-sampler (k=4) instead of CUR-sampler (k=4) (ablation)CCKD · MSMT17mAP: 30.2 -> 31.1Improved
increase images per class k from 4 to 20 in CUR-sampler (ablation)CCKD · MSMT17mAP: 30.2 -> 10.7Hurt
increase images per class k from 4 to 20 in SUR-sampler (ablation)CCKD · MSMT17mAP: 31.1 -> 13.7Hurt

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