Related papers: SCMix: Stochastic Compound Mixing for Open Compoun…

Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level adversarial learning methods only consider adapting models…

Neural networks are known to be data hungry and domain sensitive, but it is nearly impossible to obtain large quantities of labeled data for every domain we are interested in. This necessitates the use of domain adaptation strategies. One…

In the face of the deep learning model's vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although…

Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt model weights based on target data streams, making model…

Federated domain adaptation (FDA) aims to collaboratively transfer knowledge from source clients (domains) to the related but different target client, without communicating the local data of any client. Moreover, the source clients have…

Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by…

Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples…

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and…

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

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…

Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically…

Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling…

Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Current approaches often fail to leverage semantic…

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…

Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to learn a model from several labeled source domains while performing well on a different target domain where only unlabeled data are available at training time. To align…

Domain Adaptation (DA) techniques are important for overcoming the domain shift between the source domain used for training and the target domain where testing takes place. However, current DA methods assume that the entire target domain is…

Source-free domain adaptation (SFDA), where only a pre-trained source model is used to adapt to the target distribution, is a more general approach to achieving domain adaptation in the real world. However, it can be challenging to capture…

In this paper, we introduce a novel framework for the challenging problem of One-Shot Unsupervised Domain Adaptation (OSUDA), which aims to adapt to a target domain with only a single unlabeled target sample. Unlike existing approaches that…

Unsupervised Domain Adaptation (UDA) has emerged as a powerful solution for the domain shift problem via transferring the knowledge from a labeled source domain to a shifted unlabeled target domain. Despite the prevalence of UDA for visual…

Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…