# Unsupervised Compound Domain Adaptation for Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2105.08463 · HTML: https://mlsanity.com/paper/2105.08463/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 18 May 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [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)
- [CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations](https://mlsanity.com/paper/2007.12342/) (2020)
- [Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization](https://mlsanity.com/paper/1510.04373/) (2015)
- [face anti-spoofing based on color texture analysis](https://mlsanity.com/paper/1511.06316/) (2015)
- [Learn Convolutional Neural Network for Face Anti-Spoofing](https://mlsanity.com/paper/1408.5601/) (2014)
- [Open Compound Domain Adaptation](https://mlsanity.com/paper/1909.03403/) (2019)
- [Face De-Spoofing: Anti-Spoofing via Noise Modeling](https://mlsanity.com/paper/1807.09968/) (2018)
- [Deep Representations for Iris, Face, and Fingerprint Spoofing Detection](https://mlsanity.com/paper/1410.1980/) (2014)
- [Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing](https://mlsanity.com/paper/1912.07124/) (2019)
- [A Survey On Anti-Spoofing Methods For Face Recognition with RGB Cameras of Generic Consumer Devices](https://mlsanity.com/paper/2010.04145/) (2020)
- [Face Anti-Spoofing by Learning Polarization Cues in a Real-World Scenario](https://mlsanity.com/paper/2003.08024/) (2020)

## Built on by (most cited first, 6 of 6)

- [Gradient Alignment for Cross-Domain Face Anti-Spoofing](https://mlsanity.com/paper/2402.18817/) (2024)
- [Test-Time Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2403.19334/) (2024)
- [FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection](https://mlsanity.com/paper/2501.02892/) (2025)
- [Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics](https://mlsanity.com/paper/2308.14551/) (2023)
- [Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2503.22984/) (2025)
- [Deep Learning meets Liveness Detection: Recent Advancements and Challenges](https://mlsanity.com/paper/2112.14796/) (2021)

## Abstract (arXiv)

We address the problem of face anti-spoofing which aims to make the face verification systems robust in the real world settings. The context of detecting live vs. spoofed face images may differ significantly in the target domain, when compared to that of labeled source domain where the model is trained. Such difference may be caused due to new and unknown spoof types, illumination conditions, scene backgrounds, among many others. These varieties of differences make the target a compound domain, thus calling for the problem of the unsupervised compound domain adaptation. We demonstrate the effectiveness of the compound domain assumption for the task of face anti-spoofing, for the first time in this work. To this end, we propose a memory augmentation method for adapting the source model to the target domain in a domain aware manner. The adaptation process is further improved by using the curriculum learning and the domain agnostic source network training approaches. The proposed method successfully adapts to the compound target domain consisting multiple new spoof types. Our experiments on multiple benchmark datasets demonstrate the superiority of the proposed method over the state-of-the-art.