Unified multi-level neighbor clustering for Source-Free Unsupervised Domain Adaptation

Open Webpage

Yuzhe Xiao, Guangyi Xiao, Hao Chen

Published: 01 Jan 2024, Last Modified: 13 Nov 2024Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•An unified and complementary multi-level neighbor clustering method to solve SFUDA problem.•A dot-product loss is used to filter unreliable samples with ambiguous features.•The consistency of the labels of neighbors is used to reduce unconfident samples.