,Layer-wise domain correction for unsupervised domain adaptation

• 作 者: Shuang LI Shi-ji SONG Cheng WU
• 机 构: Automation Department, Tsinghua University, Beijing 100084, China
• 出 处: 信息与电子工程前沿（英文版）
• 发表日期: 2018年1期
• 关键词: Unsupervised domain adaptation Maximum mean discrepancy Residual network Deep le

Deep neural networks have been successfully applied to numerous machine leaing tasks because of their impressive feature abstraction capabilities. However, conventional deep networks assume that the training and test data are sampled from the same distribution, and this assumption is often violated in real-world scenarios. To address the domain shift or data bias problems, we introduce layer-wise domain correction (LDC), a new unsupervised domain adaptation algorithm which adapts an existing deep network through additive correction layers spaced throughout the network. Through the additive layers, the representations of source and target domains can be perfectly aligned. The corrections that are trained via maximum mean discrepancy, adapt to the target domain while increasing the representational capacity of the network. LDC requires no target labels, achieves state-of-the-art performance across several adaptation benchmarks, and requires significantly less training time than existing adaptation methods.