Related papers: Abduction-Deduction Entanglement: Domain Generaliz…
We consider the problem of learning a set of direct causes of a target variable from an observational joint distribution. Learning directed acyclic graphs (DAGs) that represent the causal structure is a fundamental problem in science.…
In this paper, we investigate a challenging unsupervised domain adaptation setting -- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model…
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…
In this paper, we propose the problem of domain transfer structured output learn- ing and the first solution to solve it. The problem is defined on two different data domains sharing the same input and output spaces, named as source domain…
Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, even when their classes are not fully shared. Few dedicated UniDA methods exist for Time Series (TS), which remains a…
Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution. In this work, we present approximate label…
Classifier predictions often rely on the assumption that new observations come from the same distribution as training data. When the underlying distribution changes, so does the optimal classification rule, and performance may degrade. We…
Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often involve only a handful of target samples, potentially lying…
Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…
Recent domain generalization (DG) approaches typically use the hypothesis learned on source domains for inference on the unseen target domain. However, such a hypothesis can be arbitrarily far from the optimal one for the target domain,…
The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the "in-domain" test data is drawn from a distribution…
Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making…
We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretically show that, for good generalization, it is necessary to…
In distributed detection, there does not exist an automatic way of generating optimal decision strategies for non-affine decision functions. Consequently, in a detection problem based on a non-affine decision function, establishing…
Recent advances in diffusion and flow matching models have highlighted a shift in the preferred prediction target -- moving from noise ($\varepsilon$) and velocity (v) to direct data (x) prediction -- particularly in high-dimensional…
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data by joint optimization over source data and target data.…
We aim for source-free domain adaptation, where the task is to deploy a model pre-trained on source domains to target domains. The challenges stem from the distribution shift from the source to the target domain, coupled with the…
Many existing transfer learning methods rely on leveraging information from source data that closely resembles the target data. However, this approach often overlooks valuable knowledge that may be present in different yet potentially…
Unsupervised domain adaptation challenges the problem of transferring knowledge from a well-labelled source domain to an unlabelled target domain. Recently,adversarial learning with bi-classifier has been proven effective in pushing…
The recent advances in deep learning predominantly construct models in their internal representations, and it is opaque to explain the rationale behind and decisions to human users. Such explainability is especially essential for domain…