Shaocong Long, Qianyu Zhou, Chenhao Ying, Lizhuang Ma, Yuan Luo
TL;DR域泛化的新观点,创造了具有强大可辨别性和鲁棒普适性的特征,通过Selective Channel Pruning和Micro-level Distribution Alignment两个核心组件,解决了当前域泛化中特征泛化和差异化挑战。
Abstract
domain generalization (DG) endeavors to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques tend to improve the →