# Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing

arXiv: https://arxiv.org/abs/2110.09157 · HTML: https://mlsanity.com/paper/2110.09157/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection](https://mlsanity.com/paper/1907.04047/) (2019)
- [Deep Tree Learning for Zero-shot Face Anti-Spoofing](https://mlsanity.com/paper/1904.02860/) (2019)
- [Face Anti-Spoofing Via Disentangled Representation Learning](https://mlsanity.com/paper/2008.08250/) (2020)
- [Face Anti-Spoofing with Human Material Perception](https://mlsanity.com/paper/2007.02157/) (2020)
- [On Disentangling Spoof Trace for Generic Face Anti-Spoofing](https://mlsanity.com/paper/2007.09273/) (2020)
- [Face De-Spoofing: Anti-Spoofing via Noise Modeling](https://mlsanity.com/paper/1807.09968/) (2018)
- [ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes](https://mlsanity.com/paper/1803.10562/) (2018)
- [Learning Meta Model for Zero- and Few-shot Face Anti-spoofing](https://mlsanity.com/paper/1904.12490/) (2019)
- [Multi-Modal Face Anti-Spoofing Based on Central Difference Networks](https://mlsanity.com/paper/2004.08388/) (2020)
- [Learning Generalized Spoof Cues for Face Anti-spoofing](https://mlsanity.com/paper/2005.03922/) (2020)

## Built on by (most cited first, 10 of 10)

- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)
- [DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection](https://mlsanity.com/paper/2304.03323/) (2023)
- [Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing](https://mlsanity.com/paper/2212.03943/) (2022)
- [InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing](https://mlsanity.com/paper/2507.12060/) (2025)
- [An Identity-Preserved Framework for Human Motion Transfer](https://mlsanity.com/paper/2204.06862/) (2022)
- [LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention](https://mlsanity.com/paper/2506.02083/) (2025)
- [Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering](https://mlsanity.com/paper/2604.27364/) (2026)
- [FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detection](https://mlsanity.com/paper/2308.10236/) (2023)
- [Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofing](https://mlsanity.com/paper/2412.17541/) (2024)

## Abstract (arXiv)

As face recognition is widely used in diverse security-critical applications, the study of face anti-spoofing (FAS) has attracted more and more attention. Several FAS methods have achieved promising performances if the attack types in the testing data are the same as training data, while the performance significantly degrades for unseen attack types. 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. Unlike previous FAS disentanglement works with one-stage architecture, we found that the dual-stage training design can improve the training stability and effectively encode the features to detect unseen attack types. Our experiments show that the proposed method provides superior accuracy than the state-of-the-art methods on several cross-type FAS benchmarks.