AI Navigate
インサイト最新記事AI大全カオスマップ

Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion

arXiv cs.CV / 4/13/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research
Read original →
共有:

Key Points

  • The paper addresses the challenge that face anti-spoofing (FAS) models often fail under unseen visual domains and spoofing methods due to limited dataset diversity.
  • It proposes PCGAN (Pattern Conversion GAN) to improve domain generalization by disentangling latent representations of facial features and spoof artifacts and generating images with varied artifact patterns.
  • The approach combines patch-based learning and multi-task training to better handle partial attacks and reduce overfitting to facial features.
  • Experimental results reported in the paper indicate improved performance both for domain generalization and for detecting partial spoofing attacks, aiming to strengthen face recognition security.

Abstract

Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing their ability to handle unseen visual domains and spoofing methods. We introduce the Pattern Conversion Generative Adversarial Network (PCGAN) to enhance domain generalization in FAS. PCGAN effectively disentangles latent vectors for spoof artifacts and facial features, allowing to generate images with diverse artifacts. We further incorporate patch-based and multi-task learning to tackle partial attacks and overfitting issues to facial features. Our extensive experiments validate PCGAN's effectiveness in domain generalization and detecting partial attacks, giving a substantial improvement in facial recognition security.

関連おすすめサービス

※当サイトはアフィリエイト広告を利用しています
🎧

Notta搭載AI議事録イヤホン ZENCHORD1

AI時代の仕事術。Notta搭載で会議の議事録を自動生成するスマートイヤホン。

🎙️

AI搭載ボイスレコーダー Plaud

世界100万人が愛用。AIで文字起こし・要約を自動化するボイスレコーダー。

🖼️

画像高画質化AIツール Aiarty Image Enhancer

AIで画像を高画質化。写真・イラストを簡単にアップスケール。