The Role of Embedding Complexity in Domain-invariant Representations
Unsupervised domain adaptation aims to generalize the hypothesis trained in a source domain to an unlabeled target domain. One popular approach to this problem is to learn a domain-invariant representation for both domains. In this work, we study, theoretically and empirically, the explicit effect of the embedding on generalization to the target domain. In particular, the complexity of the class of embeddings affects an upper bound on the target domain's risk. This is reflected in our experiments, too.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
The Role of Embedding Complexity in Domain-invariant Representations
Unsupervised domain adaptation aims to generalize the hypothesis trained in a source domain to an unlabeled target domain. One popular approach to this problem is to learn domain-invariant embeddings for both domains. In…
Domain AdaptationSensitivityUnsupervised Domain AdaptationPOEM: Polarization of Embeddings for Domain-Invariant Representations
Handling out-of-distribution samples is a long-lasting challenge for deep visual models. In particular, domain generalization (DG) is one of the most relevant tasks that aims to train a model with a generalization capabi…
Domain GeneralizationPhilosophyUnderstanding and Estimating the Adaptability of Domain-Invariant Representations
Learning domain-invariant representations is a popular approach to unsupervised domain adaptation, i.e., generalizing from a source domain with labels to an unlabeled target domain. In this work, we aim to better underst…
Domain AdaptationModel SelectionUnsupervised Domain AdaptationDomain Generalization In Robust Invariant Representation
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scena…
Domain GeneralizationObject RecognitionDomain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
Domain Adaptation (DA) has the potential to greatly help the generalization of deep learning models. However, the current literature usually assumes to transfer the knowledge from the source domain to a specific known ta…
AnatomyDisentanglementDomain AdaptationGenerative Adversarial Network+1