Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation

2024/03/12 by Αναστάσιος Αρσένος, Dimitrios Kollias, Arsenos, Anastasios +7 · 3 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Flow Measurement and Analysis #Water Systems and Optimization

paper · pdf · doi:10.48550/arxiv.2403.07514

openalex publication_date 2024/03/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift
• Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds
• Proactive HIV Care: AI-Based Comorbidity Prediction from Routine EHR Data

Related

• Uncertainty-guided Model Generalization to Unseen Domains
• Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach
• A Simple Framework for Uncertainty in Contrastive Learning
• Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)
• Causality-based Dual-Contrastive Learning Framework for Domain Generalization