Contrastive Domain Adaptation
Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains largely underexplored. In this paper, we propose to extend contrastive learning to a new domain adaptation setting, a particular situation occurring where the similarity is learned and deployed on samples following different probability distributions without access to labels. Contrastive learning learns by comparing and contrasting positive and negative pairs of samples in an unsupervised setting without access to source and target labels. We have developed a variation of a recently proposed contrastive learning framework that helps tackle the domain adaptation problem, further identifying and removing possible negatives similar to the anchor to mitigate the effects of false negatives. Extensive experiments demonstrate that the proposed method adapts well, and improves the performance on the downstream domain adaptation task.
History
School affiliated with
- College of Health and Science (Research Outputs)
- School of Computer Science (Research Outputs)
Publication Title
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Publisher
IEEEExternal DOI
ISBN
979-8-3503-0250-9eISBN
979-8-3503-0249-3Date Accepted
2021-04-18Date of Final Publication
2021-09-01Event Name
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Event Dates
19-25 June 2021Event Organiser
IEEE/CVF, Nashville, TN, USAOpen Access Status
- Open Access