Related papers: DiGA: Distil to Generalize and then Adapt for Doma…

Segmentation is a crucial analysis task in biomedical imaging. Given the diverse experimental settings in this field, the lack of generalization limits the use of deep learning in practice. Domain adaptation is a promising remedy: it…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing…

Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models' adaptation ability in general computer vision. However, different from the natural images, there exist huge semantic gaps for the nuclei from…

Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…

We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…

Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains. However, existing domain generalization approaches often bring in prediction-irrelevant…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Source-free domain adaptation aims to adapt deep neural networks using only pre-trained source models and target data. However, accessing the source model still has a potential concern about leaking the source data, which reveals the…

Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…

Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are…

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic…

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…

As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for enhancing model robustness across diverse environments. Contrastive Language-Image Pretraining (CLIP) plays a significant role in…

In medical image segmentation, domain generalization poses a significant challenge due to domain shifts caused by variations in data acquisition devices and other factors. These shifts are particularly pronounced in the most common…

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data…

Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning. However, most self-supervised and deep clustering techniques rely heavily on data augmentation, rendering them…

An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models. Domain Generalization (DG) aims to achieve this goal. However, most DG…

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…