Adaptive margin for unsupervised domain adaptation without source data

doi:10.1016/j.cviu.2025.104455

Adaptive margin for unsupervised domain adaptation without source data

2025-07-29

0

PRE

AI

DOI：10.1016/j.cviu.2025.104455

Original

Original request for help

Save

Abstract

En 中文

• A cutting-edge framework called AM-SFDA, which effectively addresses SFDA problem. • History of margins plays a crucial role in the stability of deep learning models. • The proposed method can achieve state-of-the-art performance under SFDA scenario.

Keywords:

AM-SFDA

SFDA

deep learning

margin history

state-of-the-art performance

Adaptive margin for unsupervised domain adaptation without source data

Abstract

Journal

Organization