Name
Title | ||
|---|---|---|
Learning to Augment Face Presentation Attack Dataset via Disentangled Feature Learning from Limited Spoof Data |
Abstract | ||
|---|---|---|
Face presentation attack detection methods have been de-veloped to counter presentation attacks and achieved consid-erable success, thanks to large training data and newly developed deep-learning technology. However, when encountering the attacks provided with few training examples, the learning-based detection methods tend to overfit to the small dataset and lead to poor generalization. In this paper, we study this scenario and propose to augment the limited data via disentangled feature learning. We include the live/spoof classifi-cation task and the person identification task in a multi-task learning framework to disentangle the liveness and identity features. To enlarge the number of training samples, we de-sign two remixing strategies on the disentangled features under the identity preservation constraint and the reconstruction constraint, and also adopt the idea of contrastive learning to ensure the discriminability of the augmented samples. Exper-imental results on several benchmark datasets show that the proposed augmentation method significantly improves many detection methods under the limited data scenario. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/ICME52920.2022.9859657 | 2022 IEEE International Conference on Multimedia and Expo (ICME) |
Keywords | DocType | ISSN |
Face presentation attack detection,dis-entangled feature learning,multi-task learning,contrastive learning,limited training data | Conference | 1945-7871 |
ISBN | Citations | PageRank |
978-1-6654-8564-7 | 0 | 0.34 |
References | Authors | |
2 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Pei-Kai Huang | 1 | 0 | 0.34 |
| Chu-Ling Chang | 2 | 0 | 0.34 |
| Hui-Yu Ni | 3 | 0 | 0.34 |
| Chiou-Ting Hsu | 4 | 1 | 1.03 |