Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation

2024-03-12 · Anastasios Arsenos, Dimitrios Kollias, Evangelos Petrongonas, Christos Skliros, Stefanos Kollias

In the context of single domain generalisation, the objective is for models that have been exclusively trained on data from a single domain to demonstrate strong performance when confronted with various unfamiliar domains. In this paper, we introduce a novel model referred to as Contrastive Uncertainty Domain Generalisation Network (CUDGNet). The key idea is to augment the source capacity in both input and label spaces through the fictitious domain generator and jointly learn the domain invariant representation of each class through contrastive learning. Extensive experiments on two Single Source Domain Generalisation (SSDG) datasets demonstrate the effectiveness of our approach, which surpasses the state-of-the-art single-DG methods by up to $7.08\%$. Our method also provides efficient uncertainty estimation at inference time from a single forward pass through the generator subnetwork.

📄 PDF Abstract BibTeX arXiv:2403.07514

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Uncertainty-guided Model Generalization to Unseen Domains

2021-03-12 · CVPR 2021 1 · Fengchun Qiao, Xi Peng

We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. T…

Domain Generalization image-classification Image Classification Meta-Learning+6

Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation

2023-03-07 · CVPR 2023 1 · Mattia Litrico, Alessio Del Bue, Pietro Morerio

Standard Unsupervised Domain Adaptation (UDA) methods assume the availability of both source and target data during the adaptation. In this work, we investigate Source-free Unsupervised Domain Adaptation (SF-UDA), a spec…

Domain Adaptation Source-Free Domain Adaptation Unsupervised Domain Adaptation

Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation

2024-04-16 · Mattia Litrico, Davide Talon, Sebastiano Battiato, Alessio Del Bue 외

Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source and target data. Moreover, UDA approach…

Contrastive Learning Domain Adaptation Novel Class Discovery Unsupervised Domain Adaptation

Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment

2025-09-12 · Rini Smita Thakur, Rajeev Ranjan Dwivedi, Vinod K Kurmi arxiv

Accurate segmentation of the optic disc and cup is critical for the early diagnosis and management of ocular diseases such as glaucoma. However, segmentation models trained on one dataset often suffer significant perform…

Source-Free Domain Adaptation Contrastive Learning

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

2024-12-18 · Jing Wang, Wonho Bae, Jiahong Chen, Kuangen Zhang 외

Source-free domain adaptation (SFDA) involves adapting a model originally trained using a labeled dataset ({\em source domain}) to perform effectively on an unlabeled dataset ({\em target domain}) without relying on any …

Continual Learning Contrastive Learning Domain Adaptation Informativeness+1