figshare
Browse

Contrastive Domain Adaptation

Download (537.55 kB)
conference contribution
posted on 2024-04-17, 13:23 authored by Mamatha ThotaMamatha Thota, Georgios LeontidisGeorgios Leontidis

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

IEEE

ISBN

979-8-3503-0250-9

eISBN

979-8-3503-0249-3

Date Accepted

2021-04-18

Date of Final Publication

2021-09-01

Event Name

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Event Dates

19-25 June 2021

Event Organiser

IEEE/CVF, Nashville, TN, USA

Open Access Status

  • Open Access

Publisher statement

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Usage metrics

    University of Lincoln (Research Outputs)

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC