AI Paper Atlas

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

Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition

Xiaobo Wang, Tianyu Fu, Shengcai Liao, Shuo Wang, Zhen Lei, Tao Mei

ECCV 2020 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 62 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 feature consistency instead of probability consistency (ablation)MobileFaceNet student · MegaFace identificationRank-1 accuracy (%): 69.33 -> 83.96Improved
make feature consistency hardness-aware (HFC) (ablation)feature consistency distillation · MegaFace identificationRank-1 accuracy (%): 83.96 -> 84.19Improved
add softmax-based one-hot loss to feature consistency (ablation)feature consistency distillation · MegaFace identificationRank-1 accuracy (%): 83.96 -> 81.90Hurt
add softmax loss to probability consistency (ablation)probability consistency distillation · MegaFace identificationRank-1 accuracy (%): 69.33 -> 81.74Improved
add weight decay (5e-4 instead of 0) to feature consistency (ablation)(1/2)MobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 51.65 -> 74.32Improved
add weight exclusivity to feature consistency (ablation)(1/2)MobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 74.32 -> 75.29Improved
replace orthogonality regularization with weight exclusivity (ablation)(1/2)MobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 67.80 -> 75.29Improved
replace MHE with weight exclusivity (ablation)(1/2)MobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 74.58 -> 75.29Improved
double the number of filters (2x) versus originalMobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 83.96 -> 87.19Improved
shrink filters to 1/8 of originalMobileFaceNet with FC · MegaFace identificationRank-1 accuracy (%): 83.96 -> 25.32Hurt
use EC-KD instead of KD under 30% symmetric label noise(1/2)MobileFaceNet student · MegaFace identificationRank-1 accuracy (%): 25.53 -> 75.98Improved
train EC-KD on IQIYI-VID-Training instead of the student alone(1/2)MobileFaceNet student · MegaFace identification (IQIYI-VID training)Rank-1 accuracy (%): 29.62 -> 64.27Improved

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