Adversarial Discriminative Heterogeneous Face Recognition

Authors

  • Lingxiao Song Center for Research on Intelligent Perception and Computing, CASIA
  • Man Zhang Center for Research on Intelligent Perception and Computing, CASIA
  • Xiang Wu Center for Research on Intelligent Perception and Computing, CASIA
  • Ran He Center for Research on Intelligent Perception and Computing, CASIA

Abstract

The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via adversarial learning on both raw-pixel space and compact feature space. This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network. In the pixel space, we make use of generative adversarial networks to perform cross-spectral face hallucination. An elaborate two-path model is introduced to alleviate the lack of paired images, which gives consideration to both global structures and local textures. In the feature space, an adversarial loss and a high-order variance discrepancy loss are employed to measure the global and local discrepancy between two heterogeneous distributions respectively. These two losses enhance domain-invariant feature learning and modality independent noise removing. Experimental results on three NIR-VIS databases show that our proposed approach outperforms state-of-the-art HFR methods, without requiring of complex network or large-scale training dataset.

Downloads

Published

2018-04-27

How to Cite

Song, L., Zhang, M., Wu, X., & He, R. (2018). Adversarial Discriminative Heterogeneous Face Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12291