Deep Subdomain Adaptation Network for Image Classification

For a target task where the labeled data are unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to subdomain adaptation that focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods that contain several loss functions and…

• NN
  National Natural Science Foundation of China

  Awards: U1836206, U1811461, 61773361
• CA
  Chinese Academy of Sciences

  Award: 2017146
• NK
  National Key Research and Development Program of China

  Award: 2018YFB1004300