paper-with-me

홈 › Papers

Gradient Alignment for Cross-Domain Face Anti-Spoofing

2024-02-29 · CVPR 2024 1 · Binh M. Le, Simon S. Woo

Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have garnered considerable attention. Traditional methods have focused on designing learning objectives and additional modules to isolate domain-specific features while retaining domain-invariant characteristics in their representations. However, such approaches often lack guarantees of consistent maintenance of domain-invariant features or the complete removal of domain-specific features. Furthermore, most prior works of DG for FAS do not ensure convergence to a local flat minimum, which has been shown to be advantageous for DG. In this paper, we introduce GAC-FAS, a novel learning objective that encourages the model to converge towards an optimal flat minimum without necessitating additional learning modules. Unlike conventional sharpness-aware minimizers, GAC-FAS identifies ascending points for each domain and regulates the generalization gradient updates at these points to align coherently with empirical risk minimization (ERM) gradient updates. This unique approach specifically guides the model to be robust against domain shifts. We demonstrate the efficacy of GAC-FAS through rigorous testing on challenging cross-domain FAS datasets, where it establishes state-of-the-art performance. The code is available at https://github.com/leminhbinh0209/CVPR24-FAS.

📄 PDF Abstract BibTeX arXiv:2402.18817

Code (1)

leminhbinh0209/cvpr24-fas 공식 구현 pytorch

Tasks

Domain GeneralizationFace Anti-Spoofing

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Invariant Gradient Alignment for Robust Reasoning Distillation

2026-06-03 · Zehua Cheng, Wei Dai, Jiahao Sun arxiv

Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even when the logical structure is identical. Th…

Knowledge Distillation

Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces

2025-12-08 · Prithila Angkan, Amin Jalali, Paul Hungler, Ali Etemad arxiv

We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representations for brain-computer interfaces. Our model leverages graph…

Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing

2024-01-02 · Zhe Kong, Wentian Zhang, Tao Wang, Kaihao Zhang 외

Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Although many face anti-spoofing (FAS) methods …

Adversarial AttackFace Anti-SpoofingFace RecognitionKnowledge Distillation

Continual Safety Alignment via Gradient-Based Sample Selection

2026-04-19 · Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran arxiv

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, trut…

Over-the-Air Semantic Alignment with Stacked Intelligent Metasurfaces

2025-12-05 · Mario Edoardo Pandolfo, Kyriakos Stylianopoulos, George C. Alexandropoulos, Paolo Di Lorenzo arxiv

Semantic communication systems aim to transmit task-relevant information between devices capable of artificial intelligence, but their performance can degrade when heterogeneous transmitter-receiver models produce misali…

Semantic Communication