Related papers: Learning Smooth Representation for Unsupervised Do…
Distribution shifts and adversarial examples are two major challenges for deploying machine learning models. While these challenges have been studied individually, their combination is an important topic that remains relatively…
Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case,…
Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level adversarial learning methods only consider adapting models…
This paper demonstrates the robustness of Lipschitz-regularized $\alpha$-divergences as objective functionals in generative modeling, showing they enable stable learning across a wide range of target distributions with minimal assumptions.…
Deep learning models in computational pathology often fail to generalize across cohorts and institutions due to domain shift. Existing approaches either fail to leverage unlabeled data from the target domain or rely on image-to-image…
In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-based domain adaptation methods generally ignore the changes…
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…
Domain adaptation (DA) addresses the challenge of transferring knowledge from a source domain to a target domain where image data distributions may differ. Existing DA methods often require access to source domain data, adversarial…
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such…
In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard…
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the…
As machine learning models are increasingly deployed in dynamic environments, it becomes paramount to assess and quantify uncertainties associated with distribution shifts. A distribution shift occurs when the underlying data-generating…
In practice, the data distribution at test time often differs, to a smaller or larger extent, from that of the original training data. Consequentially, the so-called source classifier, trained on the available labelled data, deteriorates on…
Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…
We propose the discrepancy-based generalization theories for unsupervised domain adaptation. Previous theories introduced distribution discrepancies defined as the supremum over complete hypothesis space. The hypothesis space may contain…
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to…
Unsupervised domain adaptation uses source data from different distributions to solve the problem of classifying data from unlabeled target domains. However, conventional methods require access to source data, which often raise concerns…
Current supervised learning models cannot generalize well across domain boundaries, which is a known problem in many applications, such as robotics or visual classification. Domain adaptation methods are used to improve these generalization…
Successful unsupervised domain adaptation is guaranteed only under strong assumptions such as covariate shift and overlap between input domains. The latter is often violated in high-dimensional applications like image classification which,…
Domain adaptation has become a widely adopted approach in machine learning due to the high costs associated with labeling data. It is typically applied when access to a labeled source domain is available. However, in real-world scenarios,…