Additive Adversarial Learning for Unbiased Authentication

Jian Liang, Yuren Cao, Chenbin Zhang, Shiyu Chang, Kun Bai, Zenglin Xu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11428-11437


Authentication is a task aiming to confirm the truth between data instances and personal identities. Typical authentication applications include face recognition, person re-identification, authentication based on mobile devices and so on. The recently-emerging data-driven authentication process may encounter undesired biases, i.e., the models are often trained in one domain (e.g., for people wearing spring outfits) while required to apply in other domains (e.g., they change the clothes to summer outfits). To address this issue, we propose a novel two-stage method that disentangles the class/identity from domain-differences, and we consider multiple types of domain-difference. In the first stage, we learn disentangled representations by a one-versus-rest disentangle learning (OVRDL) mechanism. In the second stage, we improve the disentanglement by an additive adversarial learning (AAL) mechanism. Moreover, we discuss the necessity to avoid a learning dilemma due to disentangling causally related types of domain-difference. Comprehensive evaluation results demonstrate the effectiveness and superiority of the proposed method.

Related Material

[pdf] [supp]
author = {Liang, Jian and Cao, Yuren and Zhang, Chenbin and Chang, Shiyu and Bai, Kun and Xu, Zenglin},
title = {Additive Adversarial Learning for Unbiased Authentication},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}