Skip to main content
placeholder image

Few-shot Unsupervised Domain Adaptation with Image-to-Class Sparse Similarity Encoding

Conference Paper


Abstract


  • This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.

Publication Date


  • 2021

Publisher


Citation


  • Huang, S., Yang, W., Wang, L., Zhou, L., & Yang, M. (2021). Few-shot Unsupervised Domain Adaptation with Image-to-Class Sparse Similarity Encoding. In MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia (pp. 677-685). doi:10.1145/3474085.3475232

Scopus Eid


  • 2-s2.0-85119358964

Web Of Science Accession Number


Start Page


  • 677

End Page


  • 685

Abstract


  • This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.

Publication Date


  • 2021

Publisher


Citation


  • Huang, S., Yang, W., Wang, L., Zhou, L., & Yang, M. (2021). Few-shot Unsupervised Domain Adaptation with Image-to-Class Sparse Similarity Encoding. In MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia (pp. 677-685). doi:10.1145/3474085.3475232

Scopus Eid


  • 2-s2.0-85119358964

Web Of Science Accession Number


Start Page


  • 677

End Page


  • 685