Optimal Transport for Domain Adaptation
TLDR
A regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains, that consistently outperforms state of the art approaches and can be easily adapted to the semi-supervised case where few labeled samples are available in the target domain.Abstract:
Domain adaptation is one of the most challenging tasks of modern data analytics. If the adaptation is done correctly, models built on a specific data representation become more robust when confronted to data depicting the same classes, but described by another observation system. Among the many strategies proposed, finding domain-invariant representations has shown excellent properties, in particular since it allows to train a unique classifier effective in all domains. In this paper, we propose a regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains. We learn a transportation plan matching both PDFs, which constrains labeled samples of the same class in the source domain to remain close during transport. This way, we exploit at the same time the labeled samples in the source and the distributions observed in both domains. Experiments on toy and challenging real visual adaptation examples show the interest of the method, that consistently outperforms state of the art approaches. In addition, numerical experiments show that our approach leads to better performances on domain invariant deep learning features and can be easily adapted to the semi-supervised case where few labeled samples are available in the target domain.read more
Citations
More filters
Posted Content
Computational Optimal Transport
Gabriel Peyré,Marco Cuturi +1 more
TL;DR: This short book reviews OT with a bias toward numerical methods and their applications in data sciences, and sheds lights on the theoretical properties of OT that make it particularly useful for some of these applications.
Journal ArticleDOI
A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces: A 10-year Update
Fabien Lotte,Laurent Bougrain,Andrzej Cichocki,Andrzej Cichocki,Maureen Clerc,Marco Congedo,Alain Rakotomamonjy,Florian Yger +7 more
TL;DR: A comprehensive overview of the modern classification algorithms used in EEG-based BCIs is provided, the principles of these methods and guidelines on when and how to use them are presented, and a number of challenges to further advance EEG classification in BCI are identified.
Book ChapterDOI
Deep Domain Generalization via Conditional Invariant Adversarial Networks
TL;DR: This work proposes an end-to-end conditional invariant deep domain generalization approach by leveraging deep neural networks for domain-invariant representation learning and proves the effectiveness of the proposed method.
Posted Content
Domain Adaptation for Visual Applications: A Comprehensive Survey
TL;DR: An overview of domain adaptation and transfer learning with a specific view on visual applications and the methods that go beyond image categorization, such as object detection or image segmentation, video analyses or learning visual attributes are overviewed.
Proceedings ArticleDOI
Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
TL;DR: The proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers and enables efficient distribution alignment in an end-to-end trainable fashion.
References
More filters
Journal ArticleDOI
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
Book
Network Flows: Theory, Algorithms, and Applications
TL;DR: In-depth, self-contained treatments of shortest path, maximum flow, and minimum cost flow problems, including descriptions of polynomial-time algorithms for these core models are presented.
Book
Optimal Transport: Old and New
TL;DR: In this paper, the authors provide a detailed description of the basic properties of optimal transport, including cyclical monotonicity and Kantorovich duality, and three examples of coupling techniques.
Journal ArticleDOI
Enhancing Sparsity by Reweighted ℓ 1 Minimization
TL;DR: A novel method for sparse signal recovery that in many situations outperforms ℓ1 minimization in the sense that substantially fewer measurements are needed for exact recovery.