Multi-source fully test-time adaptation

Published: 2025, Last Modified: 21 Jan 2026Neural Networks 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•New direction: propose the setting of multi-source fully test-time adaptation for the first time.•Novel method: propose an effective baseline MUTE via weighted aggregation schemes for adaptation.•Extensive evaluation: achieve state-of-the-art results on three image recognition datasets.
Loading