Abstract
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.
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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops |
| Publisher | Computer Vision Foundation (CVF) |
| Pages | 1-10 |
| Number of pages | 10 |
| DOIs | |
| Publication status | Published - 12 Jun 2021 |
Bibliographical note
AUTHOR ONLINE USEPersonal Servers. Authors and/or their employers shall have the right to post the accepted version of IEEE-copyrighted articles on their own personal servers or the servers of their institutions or employers without permission from IEEE, provided
that the posted version includes a prominently displayed IEEE copyright notice and, when published, a full citation to the original IEEE publication, including a link to the article abstract in IEEE Xplore. Authors shall not post the final, published
versions of their papers."