A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.
Code (1)
Tasks
Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Anti-Forgetting Adaptation for Unsupervised Person Re-identification
Regular unsupervised domain adaptive person re-identification (ReID) focuses on adapting a model from a source domain to a fixed target domain. However, an adapted ReID model can hardly retain previously-acquired knowled…
Domain Adaptive Person Re-IdentificationPerson Re-IdentificationUnsupervised Person Re-IdentificationUnsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation
Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift…
Unsupervised Domain AdaptationContrastive LearningPROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
This paper presents a generic framework to tackle the crucial class mismatch problem in unsupervised domain adaptation (UDA) for multi-class distributions. Previous adversarial learning methods condition domain alignmen…
Domain AdaptationObject RecognitionSemantic SegmentationUnsupervised Domain AdaptationUser Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue Systems
User Satisfaction Estimation (USE) is crucial in helping measure the quality of a task-oriented dialogue system. However, the complex nature of implicit responses poses challenges in detecting user satisfaction, and most…
Action RecognitionDomain AdaptationTask-Oriented Dialogue SystemsUnsupervised Domain AdaptationDPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
Vision-language models (VLMs), e.g., CLIP, have shown remarkable potential in zero-shot image classification. However, adapting these models to new domains remains challenging, especially in unsupervised settings where l…
Domain Adaptationimage-classificationImage ClassificationPseudo Label+2