AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Spoof Trace Disentanglement for Generic Face Anti-Spoofing

Yaojie Liu, Xiaoming Liu

TPAMI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 69 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 the trace GAN decoder (step 2) with hierarchical traces on top of step 1 (ablation)PhySTD · SiW-M Protocol I overallEER (%): 4.3 -> 2.8Improved
add synthesized spoof and harder-sample training (step 3) (ablation)PhySTD · SiW-M Protocol I overallEER (%): 2.8 -> 2.5Improved
add synthesized spoof and harder-sample training (step 3) (ablation)PhySTD · SiW-M Protocol I overallACER (%): 4.6 -> 2.8Improved
add synthesized spoof and harder-sample training (step 3) (ablation)PhySTD · SiW-M Protocol I overallTPR@FNR=0.5% (%): 89.7 -> 91.2Improved
use hierarchical multi-component traces B,C,T instead of a single trace (ablation)PhySTD Step1+Step2 · SiW-M Protocol I overallEER (%): 5.8 -> 2.8Improved
use hierarchical multi-component traces B,C,T instead of a single trace (ablation)PhySTD Step1+Step2 · SiW-M Protocol I overallACER (%): 13.8 -> 4.6Improved
add trace GAN decoder (step 2) to step 1 (ablation)PhySTD · SiW-M Protocol I overallTPR@FNR=0.5% (%): 59.3 -> 89.7Improved
add image decomposition to the auxiliary baseline (step 1) (ablation)Auxiliary FAS · SiW-M Protocol I overallEER vs ACER (%): EER 6.7 -> 4.3; ACER 6.3 -> 10.9Mixed
classify spoof medium on estimated traces instead of original imagesPhySTD traces with AlexNet · Oulu-NPU Protocol 1 5-class spoof medium classificationaccuracy (%): 80.6 -> 83.3Improved
extend ECCV preliminary version with SGF, hierarchical supervision and open-set designPhySTD · SiW-M Protocol I overallEER (relative reduction): 47.9% relative EER reduction; TDR improved by 29.5%Improved
extend ECCV preliminary version to full PhySTDPhySTD · OULU-NPU Protocols 1 and 3ACER (relative reduction): 63.6% and 32.1%Improved
apply PhySTD to unknown attacks compared with preliminary versionPhySTD · SiW-M Protocol II averageEER, ACER, TPR (relative): 11.7% EER, 19.0% ACER, 50.4% TPRImproved

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