Related papers: Energy-Based Test Sample Adaptation for Domain Gen…

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by…

The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA.…

Deep learning models perform best when tested on target (test) data domains whose distribution is similar to the set of source (train) domains. However, model generalization can be hindered when there is significant difference in the…

Machine learning traditionally assumes that the training and testing data are distributed independently and identically. However, in many real-world settings, the data distribution can shift over time, leading to poor generalization of…

We present a novel instance-based approach to handle regression tasks in the context of supervised domain adaptation under an assumption of covariate shift. The approach developed in this paper is based on the assumption that the task on…

The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance. Current techniques are not adequate for this problem because they either require detailed knowledge of…

Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent…

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the…

Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervised approaches. Recent efforts have been devoted to time…

This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the…

Traditional machine learning algorithms assume that the training and test data have the same distribution, while this assumption does not necessarily hold in real applications. Domain adaptation methods take into account the deviations in…

In domain adaptation, when there is a large distance between the source and target domains, the prediction performance will degrade. Gradual domain adaptation is one of the solutions to such an issue, assuming that we have access to…

Most previous unsupervised domain adaptation (UDA) methods for question answering(QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Source-free test-time adaptation for medical image segmentation aims to enhance the adaptability of segmentation models to diverse and previously unseen test sets of the target domain, which contributes to the generalizability and…

Supervised learning is well-known to fail at generalization under distribution shifts. In typical clinical settings, the source data is inaccessible and the target distribution is represented with a handful of samples: adaptation can only…

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g.…

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…