Adaptive Face Recognition Using Adversarial Information Network

by   Mei Wang, et al.

In many real-world applications, face recognition models often degenerate when training data (referred to as source domain) are different from testing data (referred to as target domain). To alleviate this mismatch caused by some factors like pose and skin tone, the utilization of pseudo-labels generated by clustering algorithms is an effective way in unsupervised domain adaptation. However, they always miss some hard positive samples. Supervision on pseudo-labeled samples attracts them towards their prototypes and would cause an intra-domain gap between pseudo-labeled samples and the remaining unlabeled samples within target domain, which results in the lack of discrimination in face recognition. In this paper, considering the particularity of face recognition, we propose a novel adversarial information network (AIN) to address it. First, a novel adversarial mutual information (MI) loss is proposed to alternately minimize MI with respect to the target classifier and maximize MI with respect to the feature extractor. By this min-max manner, the positions of target prototypes are adaptively modified which makes unlabeled images clustered more easily such that intra-domain gap can be mitigated. Second, to assist adversarial MI loss, we utilize a graph convolution network to predict linkage likelihoods between target data and generate pseudo-labels. It leverages valuable information in the context of nodes and can achieve more reliable results. The proposed method is evaluated under two scenarios, i.e., domain adaptation across poses and image conditions, and domain adaptation across faces with different skin tones. Extensive experiments show that AIN successfully improves cross-domain generalization and offers a new state-of-the-art on RFW dataset.


page 1

page 12


Federated Unsupervised Domain Adaptation for Face Recognition

Given labeled data in a source domain, unsupervised domain adaptation ha...

Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning

Unsupervised domain adaptation has been widely adopted to generalize mod...

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Despite outstanding performance on public benchmarks, face recognition s...

Deep face recognition with clustering based domain adaptation

Despite great progress in face recognition tasks achieved by deep convol...

Meta Balanced Network for Fair Face Recognition

Although deep face recognition has achieved impressive progress in recen...

Racial Faces in-the-Wild: Reducing Racial Bias by Deep Unsupervised Domain Adaptation

Despite of the progress achieved by deep learning in face recognition (F...

Domain adaptation for holistic skin detection

Human skin detection in images is a widely studied topic of Computer Vis...

Please sign up or login with your details

Forgot password? Click here to reset