Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training

Domain adaptation tackles the problem of transferring knowledge from a label-rich source domain to a label-scarce or even unlabeled target domain. Recently domain-adversarial training (DAT) has shown promising capacity to learn a domain-invariant feature space by reversing the gradient propagation of a domain classifier. However, DAT is still vulnerable in several aspects including (1) training instability due to the overwhelming discriminative ability of the domain classifier in adversarial training, (2) restrictive feature-level alignment, and (3) lack of interpretability or systematic explanation of the learned feature space. In this paper, we propose a novel Max-margin Domain-Adversarial Training (MDAT) by designing an Adversarial Reconstruction Network (ARN). The proposed MDAT stabilizes the gradient reversing in ARN by replacing the domain classifier with a reconstruction network, and in this manner ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures. Furthermore, ARN demonstrates strong robustness to a wide range of hyper-parameters settings, greatly alleviating the task of model selection. Extensive empirical results validate that our approach outperforms other state-of-the-art domain alignment methods. Moreover, reconstructing adapted features reveals the domain-invariant feature space which conforms with our intuition.

[1]  Yuchen Zhang,et al.  Bridging Theory and Algorithm for Domain Adaptation , 2019, ICML.

[2]  Sivaraman Balakrishnan,et al.  Optimal kernel choice for large-scale two-sample tests , 2012, NIPS.

[3]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[4]  Antonio M. López,et al.  Virtual and Real World Adaptation for Pedestrian Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

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

[10]  Yann LeCun,et al.  Energy-based Generative Adversarial Networks , 2016, ICLR.

[11]  Mo Li,et al.  Precise Power Delay Profiling with Commodity Wi-Fi , 2015, IEEE Transactions on Mobile Computing.

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

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

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

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

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

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

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

[19]  Jianmin Wang,et al.  Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation , 2019, ICML.

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

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

[22]  Roman Garnett,et al.  Bayesian optimization for automated model selection , 2016, NIPS.

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

[24]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

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

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

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

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

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

[30]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[31]  Jaime G. Carbonell,et al.  Characterizing and Avoiding Negative Transfer , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Han Zou,et al.  Consensus Adversarial Domain Adaptation , 2019, AAAI.

[33]  Luc Van Gool,et al.  Domain Adaptive Faster R-CNN for Object Detection in the Wild , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[35]  Michael I. Jordan,et al.  Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers , 2019, ICML.

[36]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

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

[38]  Michael I. Jordan,et al.  Transferable Normalization: Towards Improving Transferability of Deep Neural Networks , 2019, NeurIPS.