CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
arXiv:2003.05136
Abstract
Ethnic bias has proven to negatively affect the performance of face recognition systems, and it remains an open research problem in face anti-spoofing. In order to study the ethnic bias for face anti-spoofing, we introduce the largest up to date CASIA-SURF Cross-ethnicity Face Anti-spoofing (CeFA) dataset (briefly named CeFA), covering ethnicities, modalities, subjects, and 2D plus 3D attack types. Four protocols are introduced to measure the affect under varied evaluation conditions, such as cross-ethnicity, unknown spoofs or both of them. To the best of our knowledge, CeFA is the first dataset including explicit ethnic labels in current published/released datasets for face anti-spoofing. Then, we propose a novel multi-modal fusion method as a strong baseline to alleviate these bias, namely, the static-dynamic fusion mechanism applied in each modality (i.e., RGB, Depth and infrared image). Later, a partially shared fusion strategy is proposed to learn complementary information from multiple modalities. Extensive experiments demonstrate that the proposed method achieves state-of-the-art results on the CASIA-SURF, OULU-NPU, SiW and the CeFA dataset.
arXiv comment17 pages, 4 figures. arXiv admin note: substantial text overlap with arXiv:1912.02340
References in corpus (7)
- Face Alignment Across Large Poses: A 3D Solution
- Face Alignment in Full Pose Range: A 3D Total Solution
- Rank Pooling for Action Recognition
- Exploiting temporal and depth information for multi-frame face anti-spoofing
- Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition
- Face De-Spoofing: Anti-Spoofing via Noise Modeling
- Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings