Improving Cross-Dataset Performance of Face Presentation Attack Detection Systems Using Face Recognition Datasets

Amir Mohammadi, Sushil Bhattacharjee, Sébastien MarcelICASSP 2020 · OpenReview

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. 1
BibTeX
@inproceedings{mohammadi2020improving,
  author = {Amir Mohammadi and Sushil Bhattacharjee and Sébastien Marcel},
  title = {{Improving Cross-Dataset Performance of Face Presentation Attack Detection Systems Using Face Recognition Datasets}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  url = {https://openreview.net/forum?id=VpDZ7d9mmm},
}

Loading related content...

Figure