PDF

Description

Most models in machine learning today are fixed during deployment. As a consequence, a trained model must prepare to be robust to all possible futures, even though only one of them is actually going to happen. The basic idea of test-time training is to train on this future once it arrives in the form of a test instance. Since each test instance arrives without a ground truth label, training is performed with self-supervision. This thesis explores the first steps in realizing this idea, for images, videos and robotics.

Details

Title
Test-Time Training
Creator
Sun, Yu, Author
Published
EECS Department, University of California at Berkeley, Berkeley, California, 05/10/23
Full Collection Name
Electrical Engineering & Computer Sciences Technical Reports
Other Identifiers
EECS-2023-86
Type
Text
Format
technical reports
Extent
79 p
Language
eng
Usage Statement
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).
Collection

Files

Statistics

from
to
Export
Download Full History