Options
2024
Conference Paper
Title
Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics
Abstract
Recent face presentation attack detection (PAD) leverages domain adaptation (DA) and domain generalization (DG) techniques to address performance degradation on unknown domains. However, DA-based PAD methods require access to unlabeled target data, while most DG-based PAD solutions rely on a priori, i.e., known domain labels. Moreover, most DA-/DG-based methods are computationally intensive, demanding complex model architectures and/or multi-stage training processes. This paper proposes to model face PAD as a compound DG task from a causal perspective, linking it to model optimization. We excavate the causal factors hidden in the high-level representation via counterfactual intervention. Moreover, we introduce a class-guided MixStyle to enrich feature-level data distribution within classes instead of focusing on domain information. Both class-guided MixStyle and counterfactual intervention components introduce no extra trainable parameters and negligible computational resources. Extensive cross-dataset and analytic experiments demonstrate the effectiveness and efficiency of our method compared to state-of-the-art PADs. The implementation and the trained weights are publicly available.
Funder
Bundesministerium für Bildung und Forschung -BMBF-
Keyword(s)
Branche: Information Technology
Research Line: Computer vision (CV)
Research Line: Human computer interaction (HCI)
Research Line: Machine learning (ML)
LTA: Interactive decision-making support and assistance systems
LTA: Machine intelligence, algorithms, and data structures (incl. semantics)
LTA: Generation, capture, processing, and output of images and 3D models
Biometrics
Face recognition
Spoofing attacks
Machine learning
Deep learning
ATHENE