AI Paper Atlas

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

Meta-Teacher For Face Anti-Spoofing

Yunxiao Qin, Zitong Yu, Longbin Yan, Zezheng Wang, Chenxu Zhao, Zhen Lei

TPAMI 2021 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 92 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
supervise detector with meta-teacher instead of facial depth label (FAS-DR)FAS-DR · OULU-NPU Protocol 1ACER: 1.5 -> 0.6Improved
supervise CDCN with meta-teacher instead of depth labelCDCN · OULU-NPU Protocol 4ACER: 6.9 -> 3.7Improved
supervise DTN with meta-teacher instead of pixel-wise binary mask labelDTN · SiW-M averageACER: 16.8 -> 13.1Improved
supervise FAS-DR with meta-teacher instead of depth labelFAS-DR · SiW-M averageACER: 12.6 -> 10.5Improved
supervise FAS-DR-BC with meta-teacher instead of depth labelFAS-DR-BC · Domain generalization benchmarkHTER: 19.14 -> 11.93 (O&C&M to I)Improved
supervise RFMetaFAS with meta-teacher instead of facial depthRFMetaFAS* · Domain generalization, O&C&M to IHTER: 18.89 -> 12.77Mixed
use meta-teacher instead of Distill/BANs/Fitnet/OKDDip teachersFAS-DR · OULU-NPU Protocol 4ACER: 5.5 -> 4.3Improved
add pretraining of meta-teacher before bi-level optimization (ablation)MT-FAS · OULU-NPU Protocol 1ACER: 6.3 -> 0.6Improved
add separate MT_v to evaluate MT_t (ablation)MT-FAS · OULU-NPU Protocol 1ACER: 7.1 -> 0.6Improved
adapt surrogate detector to changing MT_t (ablation)MT-FAS · OULU-NPU Protocol 1ACER: 4.2 -> 0.6Improved
momentum gamma 0.999 versus 0.9 (ablation)MT_v update · OULU-NPU Protocol 1ACER: 5.3 -> 0.6Improved
swap meta-teacher backbone FAS-DR-Light for ResNet-8 (ablation)MT-FAS · OULU-NPU Protocol 1ACER: 0.6 -> 0.8No 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