DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization
Self-supervised learning (SSL) methods based on the instance discrimination tasks with InfoNCE have achieved remarkable success. Despite their success, SSL models often struggle to generate effective representations for unseen-domain data. To address this issue, research on unsupervised domain generalization (UDG), which aims to develop SSL models that can generate domain-irrelevant features, has been conducted. Most UDG approaches utilize contrastive learning with InfoNCE to generate representations, and perform feature alignment based on strong assumptions to generalize domain-irrelevant common features from multi-source domains. However, existing methods that rely on instance discrimination tasks are not effective at extracting domain-irrelevant common features. This leads to the suppression of domain-irrelevant common features and the amplification of domain-relevant features, thereby hindering domain generalization. Furthermore, strong assumptions underlying feature alignment can lead to biased feature learning, reducing the diversity of common features. In this paper, we propose a novel approach, DomCLP, Domain-wise Contrastive Learning with Prototype Mixup. We explore how InfoNCE suppresses domain-irrelevant common features and amplifies domain-relevant features. Based on this analysis, we propose Domain-wise Contrastive Learning (DCon) to enhance domain-irrelevant common features. We also propose Prototype Mixup Learning (PMix) to generalize domain-irrelevant common features across multiple domains without relying on strong assumptions. The proposed method consistently outperforms state-of-the-art methods on the PACS and DomainNet datasets across various label fractions, showing significant improvements. Our code will be released. Our project page is available at https://github.com/jinsuby/DomCLP.
Code (1)
Tasks
Contrastive LearningDomain GeneralizationSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation
Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes, which are represented as the central val…
Contrastive LearningDomain GeneralizationSemantic SegmentationHarnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification
Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple …
Contrastive LearningContrastive-mixup learning for improved speaker verification
This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point an…
Data AugmentationMetric LearningSpeaker VerificationContrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain
Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations…
AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup
Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationGPU+3