SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation

Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and (b) aligning the source and target domains. Traditionally, these tasks have either been considered as separate, or assumed to be implicitly addressed together with high-capacity feature extractors. When considered separately, alignment is usually viewed as a problem of aligning data distributions, either through geometric approaches such as subspace alignment or through distributional alignment such as optimal transport. This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source. The alignment is made rather simple by leveraging tractable data geometry in the form of subspaces. We synergistically allow certain parameters derived from the closed-form auxiliary solution, to be affected by gradients from the primary task. The proposed approach represents a unique fusion of geometric and model-based alignment with gradients from a data-driven primary task. Our approach termed SALT, is a simple framework that achieves comparable or sometimes outperforms state-of-the-art on multiple standard benchmarks.

[1]  Tinne Tuytelaars,et al.  Subspace Alignment For Domain Adaptation , 2014, ArXiv.

[2]  Jonathan J. Hull,et al.  A Database for Handwritten Text Recognition Research , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Tatsuya Harada,et al.  Open Set Domain Adaptation by Backpropagation , 2018, ECCV.

[4]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

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

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

[7]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[9]  Kate Saenko,et al.  Correlation Alignment for Unsupervised Domain Adaptation , 2016, Domain Adaptation in Computer Vision Applications.

[10]  Andrew J. Davison,et al.  Self-Supervised Generalisation with Meta Auxiliary Learning , 2019, NeurIPS.

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

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

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

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

[15]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

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

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

[18]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

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

[20]  Nicolas Courty,et al.  DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation , 2018, ECCV.

[21]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Vishal M. Patel,et al.  Unsupervised domain adaptation using parallel transport on Grassmann manifold , 2014, IEEE Winter Conference on Applications of Computer Vision.

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

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

[25]  Tom Schaul,et al.  Reinforcement Learning with Unsupervised Auxiliary Tasks , 2016, ICLR.

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

[27]  Daan Wierstra,et al.  One-shot Learning with Memory-Augmented Neural Networks , 2016, ArXiv.

[28]  Liang Lu,et al.  Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition , 2017, INTERSPEECH.

[29]  Marco Körner,et al.  Auxiliary Tasks in Multi-task Learning , 2018, ArXiv.

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

[31]  Diego Klabjan,et al.  Generative Adversarial Nets for Multiple Text Corpora , 2017, 2021 International Joint Conference on Neural Networks (IJCNN).

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

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

[34]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

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

[36]  Rushil Anirudh,et al.  Multiple Subspace Alignment Improves Domain Adaptation , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

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

[39]  Hong Yu,et al.  Meta Networks , 2017, ICML.

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

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

[42]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

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

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

[45]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

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

[48]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

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

[50]  Kate Saenko,et al.  Subspace Distribution Alignment for Unsupervised Domain Adaptation , 2015, BMVC.