Towards Privacy-Preserving Domain Adaptation

This study suggests a new domain adaptation paradigm that can address potential data-privacy issues. Despite promising results of existing domain adaptation methods, they have a strong constraint where the source and target samples are accessible during a training phase. However, direct usage of source samples possibly causes data-privacy issues especially when each label of source domain acts as an individual's identifier such as biometric information. To address data-privacy problems in conventional domain adaptation, we propose privacy-preserving domain adaptation (PPDA). Our main hypothesis is that if we train our target model initialized from a pre-trained source model in a self-learning manner, we can successfully transfer knowledge from a labeled source domain to an unlabeled target domain. In our preliminary study, we observe that target samples with low self-entropy measured from the pre-trained source model achieves sufficiently high accuracy. From this key observation, we first select the reliable samples based on self-entropy and define them as class prototypes. We then assign pseudo labels to the target samples through the similarity between target samples and class prototypes. To further reduce the uncertainty of the pseudo labeling process, we also introduce a sample-level reweighting scheme. Surprisingly, our PPDA model outperforms conventional domain adaptation methods on public datasets even though we do not directly access any source data.

[1]  Seong Joon Oh,et al.  Faceless Person Recognition: Privacy Implications in Social Media , 2016, ECCV.

[2]  Michael I. Jordan,et al.  Conditional Adversarial Domain Adaptation , 2017, NeurIPS.

[3]  Dumitru Erhan,et al.  Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Sungeun Hong,et al.  Attention-guided adaptation factors for unsupervised facial domain adaptation , 2020 .

[5]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Bohyung Han,et al.  Domain-Specific Batch Normalization for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[9]  Changick Kim,et al.  Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Tatsuya Harada,et al.  Maximum Classifier Discrepancy for Unsupervised Domain Adaptation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Sungeun Hong,et al.  Associative Partial Domain Adaptation , 2020, ArXiv.

[12]  Rogério Schmidt Feris,et al.  SpotTune: Transfer Learning Through Adaptive Fine-Tuning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Kate Saenko,et al.  VisDA: The Visual Domain Adaptation Challenge , 2017, ArXiv.

[14]  Hyun Seung Yang,et al.  D3: Recognizing dynamic scenes with deep dual descriptor based on key frames and key segments , 2017, Neurocomputing.

[15]  Hal Daumé,et al.  Frustratingly Easy Domain Adaptation , 2007, ACL.

[16]  Ming-Hsuan Yang,et al.  Learning to Adapt Structured Output Space for Semantic Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Jongbin Ryu,et al.  Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition , 2020, ICLR.

[18]  Kristen Grauman,et al.  Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation , 2013, ICML.

[19]  Trevor Darrell,et al.  Efficient Learning of Domain-invariant Image Representations , 2013, ICLR.

[20]  Michael I. Jordan,et al.  Deep Transfer Learning with Joint Adaptation Networks , 2016, ICML.

[21]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

[22]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[23]  Hyun Seung Yang,et al.  SSPP-DAN: Deep domain adaptation network for face recognition with single sample per person , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[24]  Edwin Lughofer,et al.  Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning , 2017, ICLR.

[25]  Tianjian Chen,et al.  Federated Machine Learning: Concept and Applications , 2019 .

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

[27]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[28]  Martine De Cock,et al.  Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation: An Application to Hate-Speech Detection , 2019, IACR Cryptol. ePrint Arch..

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

[30]  Chuan Chen,et al.  Learning Semantic Representations for Unsupervised Domain Adaptation , 2018, ICML.

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

[32]  Sungeun Hong,et al.  Unsupervised Face Domain Transfer for Low-Resolution Face Recognition , 2020, IEEE Signal Processing Letters.

[33]  Bernhard Schölkopf,et al.  Correcting Sample Selection Bias by Unlabeled Data , 2006, NIPS.

[34]  Z. Jane Wang,et al.  Median Filtering Forensics Based on Convolutional Neural Networks , 2015, IEEE Signal Processing Letters.

[35]  Tinne Tuytelaars,et al.  Unsupervised Visual Domain Adaptation Using Subspace Alignment , 2013, 2013 IEEE International Conference on Computer Vision.

[36]  Sethuraman Panchanathan,et al.  Deep Hashing Network for Unsupervised Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[38]  Masashi Sugiyama,et al.  Mixture Regression for Covariate Shift , 2006, NIPS.

[39]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.