Web: http://arxiv.org/abs/2206.08009

June 17, 2022, 1:10 a.m. | Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Deepesh Mehta, Shreyas Kulkarni, Varun Jampani, R. Venkatesh Babu

cs.LG updates on arXiv.org arxiv.org

Conventional domain adaptation (DA) techniques aim to improve domain
transferability by learning domain-invariant representations; while
concurrently preserving the task-discriminability knowledge gathered from the
labeled source data. However, the requirement of simultaneous access to labeled
source and unlabeled target renders them unsuitable for the challenging
source-free DA setting. The trivial solution of realizing an effective original
to generic domain mapping improves transferability but degrades task
discriminability. Upon analyzing the hurdles from both theoretical and
empirical standpoints, we derive novel insights to …

arxiv cv domain adaptation free

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY