Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

arXiv:2404.05094v1 Announce Type: new
Abstract: Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies.
To advance TTA under domain shifts, we propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.
We provide a learning theory analysis, demonstrating that incorporating limited labeled test instances enhances overall performances across test …

abstract advance algorithm arxiv cs.ai cs.lg data deal distribution domain novel streaming studies test type unsupervised