Related papers: Domain Game: Disentangle Anatomical Feature for Si…

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically…

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…

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the…

Since medical image data sets contain few samples and singular features, lesions are viewed as highly similar to other tissues. The traditional neural network has a limited ability to learn features. Even if a host of feature maps is…

Recent advances in deep learning methods have come to define the state-of-the-art for many medical imaging applications, surpassing even human judgment in several tasks. Those models, however, when trained to reduce the empirical risk on a…

A long standing problem in visual object categorization is the ability of algorithms to generalize across different testing conditions. The problem has been formalized as a covariate shift among the probability distributions generating the…

A deep learning model trained on some labeled data from a certain source domain generally performs poorly on data from different target domains due to domain shifts. Unsupervised domain adaptation methods address this problem by alleviating…

Fully supervised segmentation methods require a large training cohort of already segmented images, providing information at the pixel level of each image. We present a method to automatically segment and model pathologies in medical images,…

Domain generalization refers to the task of training a model which generalizes to new domains that are not seen during training. We present CSD (Common Specific Decomposition), for this setting,which jointly learns a common component (which…

Identifying new disease-related patterns in medical imaging data with the help of machine learning enlarges the vocabulary of recognizable findings. This supports diagnostic and prognostic assessment. However, image appearance varies not…

Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To…

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess…

We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly…

Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem…

Open Domain Generalization (ODG) is a challenging task as it not only deals with distribution shifts but also category shifts between the source and target datasets. To handle this task, the model has to learn a generalizable representation…

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains.…

While recent advances in deep learning (DL) for surgical scene segmentation have yielded promising results on single-center and single-imaging modality data, these methods usually do not generalize well to unseen distributions or…