Additive Adversarial Learning for Unbiased Authentication

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.

[1]  Zhe Zhao,et al.  Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations , 2017, ArXiv.

[2]  Piyush Rai,et al.  Generalized Zero-Shot Learning via Synthesized Examples , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Yong Luo,et al.  Transfer Metric Learning: Algorithms, Applications and Outlooks , 2018, Vicinagearth.

[4]  Dani Lischinski,et al.  DiDA: Disentangled Synthesis for Domain Adaptation , 2018, ArXiv.

[5]  Sebastian Nowozin,et al.  Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations , 2017, AAAI.

[6]  Adnan Amin,et al.  Fingerprint verification based on minutiae features: a review , 2004, Pattern Analysis and Applications.

[7]  Sheng-De Wang,et al.  Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[9]  Toniann Pitassi,et al.  Learning Adversarially Fair and Transferable Representations , 2018, ICML.

[10]  Gabriela Csurka,et al.  Domain Adaptation for Visual Applications: A Comprehensive Survey , 2017, ArXiv.

[11]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Huanhuan Yu,et al.  Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories , 2018, ArXiv.

[14]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[15]  Shiguang Shan,et al.  Generative Adversarial Network with Spatial Attention for Face Attribute Editing , 2018, ECCV.

[16]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[17]  Debnath Bhattacharyya,et al.  Biometric Authentication: A Review , 2009 .

[18]  Ajaz Hussain Mir,et al.  Biometrics Verification: a Literature Survey , 2011 .

[19]  Alexandros G. Dimakis,et al.  CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training , 2017, ICLR.

[20]  Mei Wang,et al.  Deep Visual Domain Adaptation: A Survey , 2018, Neurocomputing.

[21]  Jinwen Ma,et al.  DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images , 2017, ICLR.

[22]  Chris Piech,et al.  Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction , 2018, ArXiv.

[23]  Lu Zhang,et al.  FairGAN: Fairness-aware Generative Adversarial Networks , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[24]  Changshui Zhang,et al.  Attribute-Based Synthetic Network (ABS-Net): Learning more from pseudo feature representations , 2018, Pattern Recognit..

[25]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[26]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[27]  Boi Faltings,et al.  Non-Discriminatory Machine Learning through Convex Fairness Criteria , 2018, AAAI.

[28]  Blake Lemoine,et al.  Mitigating Unwanted Biases with Adversarial Learning , 2018, AIES.

[29]  Shishir K. Shah,et al.  A survey of approaches and trends in person re-identification , 2014, Image Vis. Comput..

[30]  Kush R. Varshney,et al.  Fairness GAN , 2018, IBM J. Res. Dev..

[31]  Christina Heinze-Deml,et al.  Grouping-By-ID: Guarding Against Adversarial Domain Shifts , 2017, 1710.11469.

[32]  Alexandra Chouldechova,et al.  The Frontiers of Fairness in Machine Learning , 2018, ArXiv.

[33]  Wei Shen,et al.  Learning Residual Images for Face Attribute Manipulation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[35]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[36]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Rama Chellappa,et al.  Visual Domain Adaptation: A survey of recent advances , 2015, IEEE Signal Processing Magazine.

[38]  Yunpeng Zhao,et al.  Network Inference from Temporal-Dependent Grouped Observations , 2018, Comput. Stat. Data Anal..

[39]  Alexia Jolicoeur-Martineau,et al.  The relativistic discriminator: a key element missing from standard GAN , 2018, ICLR.

[40]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[41]  Shiliang Sun,et al.  A survey of multi-source domain adaptation , 2015, Inf. Fusion.

[42]  Jinwen Ma,et al.  ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes , 2018, ECCV.