Dual Reweighting Domain Generalization for Face Presentation Attack Detection

Liu, Shubao; Zhang, Keyue; Yao, Taiping; Sheng, Kekai; Ding, Shouhong; Tai, Ying; Li, Jilin; Xie, Yuan; Ma, Lizhuang

doi:10.24963/ijcai.2021/120

Cited by 58 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Without additional constraints, a common cross-entropy classification framework is prone to overfitting on specific forged patterns (Luo et al 2021). Moreover, the quality of forgery faces is different, and optimizing each sample equally as in the traditional framework makes it difficult to uncover the underlying forgery clues and is not conducive to generalization (Liu et al 2021b;Sun et al 2021). Therefore, a new framework is urgently needed to address the above issues.…”

Section: Introductionmentioning

confidence: 99%

Dual Contrastive Learning for General Face Forgery Detection

Sun

Yao

Shen

et al. 2022

AAAI

Self Cite

107

View full text Add to dashboard Cite

With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classiﬁcation problem based on cross-entropy loss, which emphasizes category-level differences rather than the essential discrepancies between real and fake faces, limiting model generalization in unseen domains. To address this issue, we propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which specially constructs positive and negative paired data and performs designed contrastive learning at different granularities to learn generalized feature representation. Concretely, combined with the hard sample selection strategy, Inter-Instance Contrastive Learning (Inter-ICL) is ﬁrst proposed to promote task-related discriminative features learning by especially constructing instance pairs. Moreover, to further explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces by constructing local region pairs inside instances. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art competitors. Our Code is available at https://github.com/Tencent/TFace.git.

show abstract

Section: Introductionmentioning

confidence: 99%

Dual Contrastive Learning for General Face Forgery Detection

Sun

Yao

Shen

et al. 2022

AAAI

Self Cite

107

View full text Add to dashboard Cite

show abstract

“…However, these methods failed in scenarios with domain shifts. To promote the performance on new domains, Domain Generalization (DG) based methods (Chen et al 2021;Liu et al 2021b;Wang et al 2022a) and Domain Adaption (DA) methods (Wang et al 2021;Li et al 2018) are proposed. However, DG methods are unable to handle all unseen domains, resulting in subpar performance.…”

Section: Related Workmentioning

confidence: 99%

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

Hu,

Zhang,

Yao

et al. 2024

AAAI

View full text Add to dashboard Cite

Multi-Domain Face Anti-Spoofing (MD-FAS) is a practical setting that aims to update models on new domains using only novel data while ensuring that the knowledge acquired from previous domains is not forgotten. Prior methods utilize the responses from models to represent the previous domain knowledge or map the different domains into separated feature spaces to prevent forgetting. However, due to domain gaps, the responses of new data are not as accurate as those of previous data. Also, without the supervision of previous data, separated feature spaces might be destroyed by new domains while updating, leading to catastrophic forgetting. Inspired by the challenges posed by the lack of previous data, we solve this issue from a new standpoint that generates hallucinated previous data for updating FAS model. To this end, we propose a novel Domain-Hallucinated Updating (DHU) framework to facilitate the hallucination of data. Specifically, Domain Information Explorer learns representative domain information of the previous domains. Then, Domain Information Hallucination module transfers the new domain data to pseudo-previous domain ones. Moreover, Hallucinated Features Joint Learning module is proposed to asymmetrically align the new and pseudo-previous data for real samples via dual levels to learn more generalized features, promoting the results on all domains. Our experimental results and visualizations demonstrate that the proposed method outperforms state-of-the-art competitors in terms of effectiveness.

show abstract

“…On the other hand, meta-learning formulations [54,7,62] are exploited to simulate the domain shift at training time to learn a representative feature space. Furthermore, disentangled representation for spoof and ID features [61] and sample re-weighting [38] improve generalization for face anti-spoofing.…”

Section: Related Workmentioning

confidence: 99%

“…Explanation about the benchmark. We follow the typical cross-domain evaluation setting that is widely used in face anti-spoofing literature [53,22,52,24,54,7,62,61,38,73,37,35]. We note that the zero-shot benchmark proposed in [40] has been previously retrieved and is no longer available.…”

Section: A Implementation Detailsmentioning

confidence: 99%

Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing

Huang¹,

Sun²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face anti-spoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods for cross-domain face anti-spoofing using a few samples.Preprint. Under review.

show abstract

Dual Reweighting Domain Generalization for Face Presentation Attack Detection

Cited by 58 publications

References 6 publications

Dual Contrastive Learning for General Face Forgery Detection

Dual Contrastive Learning for General Face Forgery Detection

Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing

Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing

Contact Info

Product

Resources

About