Unsupervised Domain Adaptation

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

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

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

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

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

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

[7]  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).

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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