Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing

2020-11-28 · Junru Wu, Xiang Yu, Buyu Liu, Zhangyang Wang, Manmohan Chandraker

Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack. Due to the wide varieties of attacks, it is implausible to obtain training data that spans all attack types. We propose to leverage physical cues to attain better generalization on unseen domains. As a specific demonstration, we use physically guided proxy cues such as depth, reflection, and material to complement our main anti-spoofing (a.k.a liveness detection) task, with the intuition that genuine faces across domains have consistent face-like geometry, minimal reflection, and skin material. We introduce a novel uncertainty-aware attention scheme that independently learns to weigh the relative contributions of the main and proxy tasks, preventing the over-confident issue with traditional attention modules. Further, we propose attribute-assisted hard negative mining to disentangle liveness-irrelevant features with liveness features during learning. We evaluate extensively on public benchmarks with intra-dataset and inter-dataset protocols. Our method achieves the superior performance especially in unseen domain generalization for FAS.

📄 PDF Abstract BibTeX arXiv:2011.14054

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDomain Generalization Face Anti-Spoofing

SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection

2026-01-06 · Kim Jun-Seong, Tae-Hyun Oh, Eduardo Pérez-Pellitero, Youngkyoon Jang arxiv

We propose Self-Augmented Residual 3D Gaussian Splatting (SA-ResGS), a novel framework to stabilize uncertainty quantification and enhancing uncertainty-aware supervision in next-best-view (NBV) selection for active scen…

Point Clouds

Uncertainty-Aware Generative Oversampling Using an Entropy-Guided Conditional Variational Autoencoder

2025-09-29 · Amirhossein Zare, Amirhessam Zare, Parmida Sadat Pezeshki, Herlock 외 arxiv

Class imbalance remains a major challenge in machine learning, especially for high-dimensional biomedical data where nonlinear manifold structures dominate. Traditional oversampling methods such as SMOTE rely on local li…

Representation Learning

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

2023-07-03 · CVPR 2024 1 · Yuxiang Zhang, Hongwen Zhang, Liangxiao Hu, Jiajun Zhang 외

Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, due to the challenges in data collection and network designs, it remain…

3D Human Pose Estimation

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning

2026-01-20 · Zhihang Yuan, Chengyu Yue, Long Huang, Litu Ou 외 arxiv

Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning costly and often unnecessary. Existing da…

Efficient Epistemic Uncertainty Estimation for Large Language Models via Knowledge Distillation

2026-02-02 · Seonghyeon Park, Jewon Yeom, Jaewon Sok, Jeongjae Park 외 arxiv

Quantifying uncertainty in Large Language Models (LLMs) is essential for mitigating hallucinations and enabling risk-aware deployment in safety-critical tasks. However, estimating Epistemic Uncertainty(EU) via Deep Ensem…

Knowledge Distillation