A DVERSARIAL F EATURE L EARNING UNDER A CCU-RACY C ONSTRAINT FOR D OMAIN G ENERALIZATION
A DVERSARIAL F EATURE L EARNING UNDER A CCU-RACY C ONSTRAINT FOR D OMAIN G ENERALIZATION
复制标题
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. Akuzawa;Yusuke Iwasawa;Y. Matsuo
中科院分区：
文献类型：
--
作者：
K. Akuzawa;Yusuke Iwasawa;Y. Matsuo
学习域不变表示是进行域泛化的主要方法。然而，以前的基于领域不变性的方法忽略了类对领域的潜在依赖，这是在分类精度和不变性之间权衡的原因。本文提出了一种新的精度约束下的对抗特征学习方法（AFLAC），该方法在不影响精度的范围内最大化域不变性。实证验证表明，AFLAC的性能优于基线方法，支持考虑依赖性的重要性和所提出的方法克服问题的有效性。
Learning domain-invariant representation is a dominant approach for domain generalization. However, previous methods based on domain invariance overlooked the underlying dependency of classes on domains, which is responsible for the trade-off between classification accuracy and the invariance. This study proposes a novel method adversarial feature learning under accuracy constraint (AFLAC), which maximizes domain invariance within a range that does not interfere with accuracy. Empirical validations show that the performance of AFLAC is superior to that of baseline methods, supporting the importance of considering the dependency and the efficacy of the proposed method to overcome the problem.