Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work, we seek to align the learned representations of the source and target domains while preserving discriminability. The way we accomplish alignment is by learning to perform auxiliary self-supervised task(s) on both domains simultaneously. Each self-supervised task brings the two domains closer together along the direction relevant to that task. Training this jointly with the main task classifier on the source domain is shown to successfully generalize to the unlabeled target domain. The presented objective is straightforward to implement and easy to optimize. We achieve state-of-the-art results on four out of seven standard benchmarks, and competitive results on segmentation adaptation. We also demonstrate that our method composes well with another popular pixel-level adaptation method.

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

[2]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[3]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[4]  John Blitzer,et al.  Co-Training for Domain Adaptation , 2011, NIPS.

[5]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[6]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[8]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

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

[10]  Abhinav Gupta,et al.  Unsupervised Learning of Visual Representations Using Videos , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[12]  Alexei A. Efros,et al.  Unsupervised Visual Representation Learning by Context Prediction , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  George Trigeorgis,et al.  Domain Separation Networks , 2016, NIPS.

[14]  Silvio Savarese,et al.  Learning Transferrable Representations for Unsupervised Domain Adaptation , 2016, NIPS.

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

[16]  Mengjie Zhang,et al.  Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation , 2016, ECCV.

[17]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[18]  Paolo Favaro,et al.  Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles , 2016, ECCV.

[19]  Vladlen Koltun,et al.  Playing for Data: Ground Truth from Computer Games , 2016, ECCV.

[20]  Kilian Q. Weinberger,et al.  Deep Networks with Stochastic Depth , 2016, ECCV.

[21]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[22]  John D. Lafferty,et al.  Local Minimax Complexity of Stochastic Convex Optimization , 2016, NIPS.

[23]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[24]  Alexei A. Efros,et al.  Context Encoders: Feature Learning by Inpainting , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Alexei A. Efros,et al.  Colorful Image Colorization , 2016, ECCV.

[26]  Andrew Owens,et al.  Ambient Sound Provides Supervision for Visual Learning , 2016, ECCV.

[27]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Lior Wolf,et al.  Unsupervised Cross-Domain Image Generation , 2016, ICLR.

[29]  Gregory Shakhnarovich,et al.  Colorization as a Proxy Task for Visual Understanding , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Geoffrey French,et al.  Self-ensembling for domain adaptation , 2017, ArXiv.

[31]  Tengyuan Liang,et al.  How Well Can Generative Adversarial Networks (GAN) Learn Densities: A Nonparametric View , 2017, ArXiv.

[32]  J. Zico Kolter,et al.  Gradient descent GAN optimization is locally stable , 2017, NIPS.

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

[34]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[35]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

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

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

[38]  Tatsuya Harada,et al.  Asymmetric Tri-training for Unsupervised Domain Adaptation , 2017, ICML.

[39]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[40]  Alexei A. Efros,et al.  Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Andrew Zisserman,et al.  Multi-task Self-Supervised Visual Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[42]  Nicolas Courty,et al.  Optimal Transport for Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Behnam Neyshabur,et al.  Stabilizing GAN Training with Multiple Random Projections , 2017, ArXiv.

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

[45]  Ruslan Salakhutdinov,et al.  Geometry of Optimization and Implicit Regularization in Deep Learning , 2017, ArXiv.

[46]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[47]  Jerry Li,et al.  Towards Understanding the Dynamics of Generative Adversarial Networks , 2017, ArXiv.

[48]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[49]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[50]  Stefano Ermon,et al.  A DIRT-T Approach to Unsupervised Domain Adaptation , 2018, ICLR.

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

[52]  Andrew M. Dai,et al.  Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step , 2017, ICLR.

[53]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

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

[55]  Jerry Li,et al.  On the Limitations of First-Order Approximation in GAN Dynamics , 2017, ICML.

[56]  Yi Zhang,et al.  Stronger generalization bounds for deep nets via a compression approach , 2018, ICML.

[57]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

[58]  Claire Cardie,et al.  Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification , 2016, TACL.

[59]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[60]  Yang Zou,et al.  Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training , 2018, ArXiv.

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

[62]  Allan Jabri,et al.  Learning Correspondence From the Cycle-Consistency of Time , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[63]  Fabio Maria Carlucci,et al.  Domain Generalization by Solving Jigsaw Puzzles , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[64]  Michael I. Jordan,et al.  Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal , 2019, ArXiv.

[65]  Subhransu Maji,et al.  Boosting Supervision with Self-Supervision for Few-shot Learning , 2019, ArXiv.

[66]  Dawn Song,et al.  Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty , 2019, NeurIPS.

[67]  Michael I. Jordan,et al.  What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? , 2019, ICML.