Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition

Although deep learning techniques have largely improved face recognition, unconstrained surveillance face recognition is still an unsolved challenge, due to the limited training data and the gap of domain distribution. Previous methods mostly match low-resolution and high-resolution faces in different domains, which tend to deteriorate the original feature space in the common recognition scenarios. To avoid this problem, we propose resolution adaption network (RAN) which contains Multi-Resolution Generative Adversarial Networks (MR-GAN) followed by a feature adaption network. MR-GAN learns multi-resolution representations and randomly selects one resolution to generate realistic low-resolution (LR) faces that can avoid the artifacts of down-sampled faces. A novel feature adaption network with translation gate is developed to fuse the discriminative information of LR faces into backbone network, while preserving the discrimination ability of original face representations. The experimental results on IJB-C TinyFace, SCface, QMUL-SurvFace datasets have demonstrated the superiority of our method compared with state-of-the-art surveillance face recognition methods, while showing stable performance on the common recognition scenarios.