BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

Daeun Lee; Jaehong Yoon; Sung Ju Hwang

2024 ICML ICML 2024

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Daeun Lee, Jaehong Yoon, Sung Ju Hwang

Topics

Machine Learning > Application Areas > Domain Adaptation

Keywords

trainable parameter continual test-time adaptation performance gain domain-adaptive routing domain-expert synergy loss mixture-of-domain low-rank experts

Download PDF