Deep Subdomain Adaptation Network for Image Classification

TL;DR

This paper introduces DSAN, a simple and efficient deep subdomain adaptation network that aligns subdomain distributions using LMMD, improving transfer learning performance without adversarial training.

Contribution

The paper proposes a non-adversarial, fast-converging deep subdomain adaptation method using LMMD to align relevant subdomain distributions across domains.

Findings

DSAN achieves superior accuracy on object recognition and digit classification tasks.

The method converges faster and is easier to implement than adversarial approaches.

Experimental results demonstrate significant improvements over baseline methods.

Abstract

For a target task where labeled data is 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 which focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods which contain several loss functions and converge slowly. Based on this, we present Deep Subdomain Adaptation Network (DSAN) which learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at: https://github.com/easezyc/deep-transfer-learning