all AI news
Layerwise Early Stopping for Test Time Adaptation
April 8, 2024, 4:42 a.m. | Sabyasachi Sahoo, Mostafa ElAraby, Jonas Ngnawe, Yann Pequignot, Frederic Precioso, Christian Gagne
cs.LG updates on arXiv.org arxiv.org
Abstract: Test Time Adaptation (TTA) addresses the problem of distribution shift by enabling pretrained models to learn new features on an unseen domain at test time. However, it poses a significant challenge to maintain a balance between learning new features and retaining useful pretrained features. In this paper, we propose Layerwise EArly STopping (LEAST) for TTA to address this problem. The key idea is to stop adapting individual layers during TTA if the features being learned …
abstract arxiv balance challenge cs.ai cs.cv cs.lg distribution domain enabling features however learn new features paper pretrained models shift test type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineer, Data Tools - Full Stack
@ DoorDash | Pune, India
Senior Data Analyst
@ Artsy | New York City