IMPROVING CROSS-DATASET PERFORMANCE OF FACE PRESENTATION ATTACK DETECTION SYSTEMS USING FACE RECOGNITION DATASETS
| Type of publication: | Conference paper |
| Citation: | Mohammadi_InfoVAE_ICASSP_2020 |
| Publication status: | Accepted |
| Booktitle: | 45th International Conference on Acoustics, Speech, and Signal Processing |
| Year: | 2020 |
| Publisher: | IEEE |
| URL: | https://gitlab.idiap.ch/bob/bo... |
| Abstract: | Presentation attack detection (PAD) is now considered critically important for any face-recognition (FR) based access-control system. Current deep-learning based PAD systems show excellent performance when they are tested in intra-dataset scenarios. Under cross-dataset evaluation the performance of these PAD systems drops significantly. This lack of generalization is attributed to domain-shift. Here, we propose a novel PAD method that leverages the large variability present in FR datasets to induce invariance to factors that cause domain-shift. Evaluation of the proposed method on several datasets, including datasets collected using mobile devices, shows performance improvements in cross-dataset evaluations. |
| Keywords: | cross-dataset evaluation, domain generalization, mobile biometrics, Presentation Attack Detection |
| Projects |
SWAN |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
