Multi-Domain Incremental Learning for Face Presentation Attack Detection

Previous face Presentation Attack Detection (PAD) methods aim to improve the effectiveness of cross-domain tasks. However, in real-world scenarios, the original training data of the pre-trained model is not available due to data privacy or other reasons. Under these constraints, general methods for fine-tuning single-target domain data may lose previously learned knowledge, leading to the issue of catastrophic forgetting. To address these issues, we propose a Multi-Domain Incremental Learning (MDIL) method for PAD, which not only learns knowledge well from the new domain but also maintains the performance of previous domains stably. To this end, we propose an Adaptive Domain-specific Experts (ADE) framework based on the vision transformer to preserve the discriminability of previous domains. Moreover, we present an asymmetric classifier to keep the output distribution of different classifiers consistent, thereby improving the generalization ability. Extensive experiments show that our proposed method achieves state-of-the-art performance compared to prior methods of incremental learning. Excitingly, under more stringent setting conditions, our method approximates or even outperforms DA/DG-based methods.