CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

• URL: http://arxiv.org/abs/2003.05136v1
• Date: Wed, 11 Mar 2020 06:58:54 GMT
• Title: CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
• Authors: Ajian Li, Zichang Tan, Xuan Li, Jun Wan, Sergio Escalera, Guodong Guo, Stan Z. Li
• Abstract summary: We introduce the largest up to date CASIA-SURF Cross-ethnicity Face Anti-spoofing dataset (CeFA) CeFA is the first dataset including explicit ethnic labels in current published/released datasets for face anti-spoofing. We propose a novel multi-modal fusion method as a strong baseline to alleviate these bias.
• Score: 83.05878126420706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 $3$ ethnicities, $3$ modalities, $1,607$ 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.

Related papers

• Hyperbolic Face Anti-Spoofing [21.981129022417306]
  We propose to learn richer hierarchical and discriminative spoofing cues in hyperbolic space. For unimodal FAS learning, the feature embeddings are projected into the Poincar'e ball, and then the hyperbolic binary logistic regression layer is cascaded for classification. To alleviate the vanishing gradient problem in hyperbolic space, a new feature clipping method is proposed to enhance the training stability of hyperbolic models.
  arXiv  Detail & Related papers  (2023-08-17T17:18:21Z)
• Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results [73.98594459933008]
  Face anti-spoofing (FAS) is an essential mechanism for safeguarding the integrity of automated face recognition systems. This limitation can be attributed to the scarcity and lack of diversity in publicly available FAS datasets. We introduce the Wild Face Anti-Spoofing dataset, a large-scale, diverse FAS dataset collected in unconstrained settings.
  arXiv  Detail & Related papers  (2023-04-12T10:29:42Z)
• Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing [18.545438302664756]
  It is essential to learn more generalized and discriminative features to prevent overfitting to pre-defined spoof attack types. This paper proposes a novel dual-stage disentangled representation learning method that can efficiently untangle spoof-related features from irrelevant ones.
  arXiv  Detail & Related papers  (2021-10-18T10:22:52Z)
• Face Anti-Spoofing with Human Material Perception [76.4844593082362]
  Face anti-spoofing (FAS) plays a vital role in securing the face recognition systems from presentation attacks. We rephrase face anti-spoofing as a material recognition problem and combine it with classical human material perception. We propose the Bilateral Convolutional Networks (BCN), which is able to capture intrinsic material-based patterns.
  arXiv  Detail & Related papers  (2020-07-04T18:25:53Z)
• Creating Artificial Modalities to Solve RGB Liveness [79.9255035557979]
  We introduce two types of artificial transforms: rank pooling and optical flow, combined in end-to-end pipeline for spoof detection. The proposed method achieves state-of-the-art on the largest cross-ethnicity face anti-spoofing dataset CASIA-SURF CeFA (RGB)
  arXiv  Detail & Related papers  (2020-06-29T13:19:22Z)
• Look Locally Infer Globally: A Generalizable Face Anti-Spoofing Approach [53.86588268914105]
  State-of-the-art spoof detection methods tend to overfit to the spoof types seen during training and fail to generalize to unknown spoof types. We propose Self-Supervised Regional Fully Convolutional Network (SSR-FCN) that is trained to learn local discriminative cues from a face image in a self-supervised manner.
  arXiv  Detail & Related papers  (2020-06-04T13:11:17Z)
• PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing [6.655217883712949]
  We propose a novel pipeline-based multi-stream CNN architecture called PipeNet for multi-modal face anti-spoofing. The proposed method wins the third place in the final ranking of Chalearn Multi-modal Cross-ethnicity Face Anti-spoofing Recognition Challenge@CVPR 2020.
  arXiv  Detail & Related papers  (2020-04-24T13:46:00Z)
• Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review [79.49390241265337]
  Chalearn Face Anti-spoofing Attack Detection Challenge consists of single-modal (e.g., RGB) and multi-modal (e.g., RGB, Depth, Infrared (IR)) tracks. This paper presents an overview of the challenge, including its design, evaluation protocol and a summary of results.
  arXiv  Detail & Related papers  (2020-04-23T06:43:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.