Related papers: Continual BatchNorm Adaptation (CBNA) for Semantic…

Manual annotation of 3D medical images for segmentation tasks is tedious and time-consuming. Moreover, data privacy limits the applicability of crowd sourcing to perform data annotation in medical domains. As a result, training deep neural…

Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose…

While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…

This work presents an approach for incrementally updating deep neural network (DNN) models in a non-stationary environment. DNN models are sensitive to changes in input data distribution, which limits their application to problem settings…

Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However,…

Domain shift is a major problem for deploying deep networks in clinical practice. Network performance drops significantly with (target) images obtained differently than its (source) training data. Due to a lack of target label data, most…

Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

With the widespread success of deep learning in biomedical image segmentation, domain shift becomes a critical and challenging problem, as the gap between two domains can severely affect model performance when deployed to unseen data with…

Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly…

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such…

Instance segmentation is crucial for autonomous driving, but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled…

Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain. However, most of these conventional UDA approaches make the strong assumption of…

Deep Neural Networks (DNNs) have recently been achieving state-of-the-art performance on a variety of computer vision related tasks. However, their computational cost limits their ability to be implemented in embedded systems with…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…

Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some…

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…

Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images. UDA adapts…

Unsupervised Domain Adaptation (UDA) methods facilitate knowledge transfer from a labeled source domain to an unlabeled target domain, navigating the obstacle of domain shift. While Convolutional Neural Networks (CNNs) are a staple in UDA,…