Related papers: Domain Generalization via Frequency-domain-based F…

Medical image segmentation plays a crucial role in clinical workflows, but domain shift often leads to performance degradation when models are applied to unseen clinical domains. This challenge arises due to variations in imaging…

As deep learning-based systems have become an integral part of everyday life, limitations in their generalization ability have begun to emerge. Machine learning algorithms typically rely on the i.i.d. assumption, meaning that their training…

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization…

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribution (OOD) generalization is more common in practice, which…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

This paper is concerned with data-driven unsupervised domain adaptation, where it is unknown in advance how the joint distribution changes across domains, i.e., what factors or modules of the data distribution remain invariant or change…

Domain generalization (DG) aims at generalizing a classifier trained on multiple source domains to an unseen target domain with domain shift. A common pervasive theme in existing DG literature is domain-invariant representation learning…

Modern deep neural networks struggle to transfer knowledge and generalize across diverse domains when deployed to real-world applications. Currently, domain generalization (DG) is introduced to learn a universal representation from multiple…

Out-of-distribution generalization is one of the key challenges when transferring a model from the lab to the real world. Existing efforts mostly focus on building invariant features among source and target domains. Based on invariant…

AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain…

Federated Domain Generalization (FedDG), aims to tackle the challenge of generalizing to unseen domains at test time while catering to the data privacy constraints that prevent centralized data storage from different domains originating at…

Anomaly detection aims to identify abnormal data that deviates from the normal ones, while typically requiring a sufficient amount of normal data to train the model for performing this task. Despite the success of recent anomaly detection…

Advanced deepfake technologies are blurring the lines between real and fake, presenting both revolutionary opportunities and alarming threats. While it unlocks novel applications in fields like entertainment and education, its malicious use…

Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic…

Deep learning-based medical image segmentation faces significant challenges arising from limited labeled data and domain shifts. While prior approaches have primarily addressed these issues independently, their simultaneous occurrence is…

By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels. Many existing UDA algorithms suffer from directly using raw…

In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without…

Object counting models suffer when deployed across domains with differing density variety, since density shifts are inherently task-relevant and violate standard domain adaptation assumptions. To address this, we propose a theoretical…

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a…

Researchers have been facing a difficult problem that data generation mechanisms could be influenced by internal or external factors leading to the training and test data with quite different distributions, consequently traditional…