BriefGPT.xyz
Feb, 2024
基于不确定性感知自适应蒸馏的多源无域自适应
Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation
HTML
PDF
Yaxuan Song, Jianan Fan, Dongnan Liu, Weidong Cai
TL;DR
提出一种名为UAD的简单而有效方法,用于医学领域中的多源免监督域适应,通过模型层和实例层的知识蒸馏,实现高性能的目标领域模型,验证了其在两个图像诊断基准数据集上的普适性和显著性能提升。
Abstract
source-free domain adaptation
(SFDA) alleviates the domain discrepancy among data obtained from domains without accessing the data for the awareness of data privacy. However, existing conventional SFDA methods face inherent limitations in
→