Discriminative feature alignment: Improving transferability of unsupervised domain adaptation by Gaussian-guided latent alignment

作者：

Highlights：

• We propose a novel alignment method to construct a common feature space under the guidance of a Gaussian prior for UDA.

• We introduce a new method to align two distributions by minimizing the direct L1-distance between the decoded samples.

• The proposed work achieves state-of-the-art performance on both digit and object classification tasks.

摘要

•We propose a novel alignment method to construct a common feature space under the guidance of a Gaussian prior for UDA.•We introduce a new method to align two distributions by minimizing the direct L1-distance between the decoded samples.•The proposed work achieves state-of-the-art performance on both digit and object classification tasks.

论文关键词：Domain adaptation,Computer vision,Information theory

论文评审过程：Received 6 September 2020, Revised 11 February 2021, Accepted 5 March 2021, Available online 17 March 2021, Version of Record 25 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107943