# S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens

arXiv: https://arxiv.org/abs/2309.04038 · HTML: https://mlsanity.com/paper/2309.04038/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 87 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 30 of 46)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Convolutional Bypasses Are Better Vision Transformer Adapters](https://mlsanity.com/paper/2207.07039/) (2022)
- [CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations](https://mlsanity.com/paper/2007.12342/) (2020)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning](https://mlsanity.com/paper/2004.01959/) (2020)
- [Regularized Fine-grained Meta Face Anti-spoofing](https://mlsanity.com/paper/1911.10771/) (2019)
- [Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network](https://mlsanity.com/paper/1909.08848/) (2019)
- [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)
- [Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing](https://mlsanity.com/paper/2203.05340/) (2022)
- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [Face Anti-Spoofing Via Disentangled Representation Learning](https://mlsanity.com/paper/2008.08250/) (2020)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [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)
- [Less is More: Pay Less Attention in Vision Transformers](https://mlsanity.com/paper/2105.14217/) (2021)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [Revisiting Pixel-Wise Supervision for Face Anti-Spoofing](https://mlsanity.com/paper/2011.12032/) (2020)
- [Learning Meta Model for Zero- and Few-shot Face Anti-spoofing](https://mlsanity.com/paper/1904.12490/) (2019)
- [On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofing](https://mlsanity.com/paper/2011.08019/) (2020)

## Built on by (most cited first, 11 of 11)

- [Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2402.19298/) (2024)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection](https://mlsanity.com/paper/2409.09724/) (2024)
- [Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering](https://mlsanity.com/paper/2504.04470/) (2025)
- [FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models](https://mlsanity.com/paper/2505.09415/) (2025)
- [Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing](https://mlsanity.com/paper/2506.01783/) (2025)
- [FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection](https://mlsanity.com/paper/2504.00454/) (2025)
- [Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images](https://mlsanity.com/paper/2505.03611/) (2025)
- [Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitions](https://mlsanity.com/paper/2507.05575/) (2025)
- [AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solution](https://mlsanity.com/paper/2509.06282/) (2025)
- [Architectural Bias in Face Presentation Attack Detection: A Comparative Study of Vision Transformers and Convolutional Neural Networks](https://mlsanity.com/paper/2606.18510/) (2026)

## Abstract (arXiv)

Face Anti-Spoofing (FAS) aims to detect malicious attempts to invade a face recognition system by presenting spoofed faces. State-of-the-art FAS techniques predominantly rely on deep learning models but their cross-domain generalization capabilities are often hindered by the domain shift problem, which arises due to different distributions between training and testing data. In this study, we develop a generalized FAS method under the Efficient Parameter Transfer Learning (EPTL) paradigm, where we adapt the pre-trained Vision Transformer models for the FAS task. During training, the adapter modules are inserted into the pre-trained ViT model, and the adapters are updated while other pre-trained parameters remain fixed. We find the limitations of previous vanilla adapters in that they are based on linear layers, which lack a spoofing-aware inductive bias and thus restrict the cross-domain generalization. To address this limitation and achieve cross-domain generalized FAS, we propose a novel Statistical Adapter (S-Adapter) that gathers local discriminative and statistical information from localized token histograms. To further improve the generalization of the statistical tokens, we propose a novel Token Style Regularization (TSR), which aims to reduce domain style variance by regularizing Gram matrices extracted from tokens across different domains. Our experimental results demonstrate that our proposed S-Adapter and TSR provide significant benefits in both zero-shot and few-shot cross-domain testing, outperforming state-of-the-art methods on several benchmark tests. We will release the source code upon acceptance.