Adversarial Discriminative Heterogeneous Face Recognition
This work addresses the challenge of recognizing faces across different modalities (e.g., near-infrared and visible light) for security and surveillance applications, representing an incremental improvement over existing methods.
The paper tackled the problem of heterogeneous face recognition (HFR) by proposing an adversarial discriminative feature learning framework to close the sensing gap between different face modalities, achieving state-of-the-art performance on three NIR-VIS databases without complex networks or large datasets.
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.