Domain Agnostic Learning with Disentangled Representations

Unsupervised model transfer has the potential to greatly improve the generalizability of deep models to novel domains. Yet the current literature assumes that the separation of target data into distinct domains is known as a priori. In this paper, we propose the task of Domain-Agnostic Learning (DAL): How to transfer knowledge from a labeled source domain to unlabeled data from arbitrary target domains? To tackle this problem, we devise a novel Deep Adversarial Disentangled Autoencoder (DADA) capable of disentangling domain-specific features from class identity. We demonstrate experimentally that when the target domain labels are unknown, DADA leads to state-of-the-art performance on several image classification datasets.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[3]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

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

[5]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Trevor Darrell,et al.  Continuous Manifold Based Adaptation for Evolving Visual Domains , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Marios Savvides,et al.  Ring Loss: Convex Feature Normalization for Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Alex ChiChung Kot,et al.  Domain Generalization with Adversarial Feature Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Yann LeCun,et al.  Disentangling factors of variation in deep representation using adversarial training , 2016, NIPS.

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

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

[14]  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.

[15]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[16]  Yishay Mansour,et al.  Domain Adaptation with Multiple Sources , 2008, NIPS.

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

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[20]  Kate Saenko,et al.  Synthetic to Real Adaptation with Generative Correlation Alignment Networks , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[21]  Yu-Chiang Frank Wang,et al.  A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation , 2018, NeurIPS.

[22]  Mengjie Zhang,et al.  Domain Adaptive Neural Networks for Object Recognition , 2014, PRICAI.

[23]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[24]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[25]  Bo Wang,et al.  Moment Matching for Multi-Source Domain Adaptation , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[26]  Gijs Dubbelman,et al.  A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[27]  Koby Crammer,et al.  Learning from Multiple Sources , 2006, NIPS.

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

[29]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[30]  Dong Xu,et al.  Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Dacheng Tao,et al.  Domain Generalization via Conditional Invariant Representation , 2018, ArXiv.

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

[33]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

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

[36]  Michael I. Jordan,et al.  Unsupervised Domain Adaptation with Residual Transfer Networks , 2016, NIPS.

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

[38]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

[39]  Liang Lin,et al.  Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[41]  Geoffrey French,et al.  Self-ensembling for visual domain adaptation , 2017, ICLR.

[42]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[43]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[44]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[45]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[46]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[47]  Maneesh Kumar Singh,et al.  DRIT++: Diverse Image-to-Image Translation via Disentangled Representations , 2019, International Journal of Computer Vision.

[48]  Fabio Maria Carlucci,et al.  Agnostic Domain Generalization , 2018, ArXiv.

[49]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[50]  Trevor Darrell,et al.  Adapting Visual Category Models to New Domains , 2010, ECCV.

[51]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[52]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[53]  Yoshua Bengio,et al.  Mutual Information Neural Estimation , 2018, ICML.

[54]  Dacheng Tao,et al.  Domain Generalization via Conditional Invariant Representations , 2018, AAAI.

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

[56]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.