Fisher Deep Domain Adaptation

TL;DR

This paper introduces a Fisher loss to improve deep domain adaptation by learning more discriminative features, resulting in better performance on benchmark datasets when combined with existing transfer criteria.

Contribution

The paper proposes a Fisher loss that enhances feature discriminability in deep domain adaptation, improving the effectiveness of existing transfer methods.

Findings

Fisher loss improves domain adaptation performance.

Combining Fisher loss with MMD, CORAL, or adversarial loss yields significant accuracy gains.

Achieved 6.67% improvement on Office-Home dataset.

Abstract

Deep domain adaptation models learn a neural network in an unlabeled target domain by leveraging the knowledge from a labeled source domain. This can be achieved by learning a domain-invariant feature space. Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance. To fill the gap, a Fisher loss is proposed to learn discriminative representations which are within-class compact and between-class separable. Experimental results on two benchmark datasets show that the Fisher loss is a general and effective loss for deep domain adaptation. Noticeable improvements are brought when it is used together with widely adopted transfer criteria, including MMD, CORAL and domain adversarial loss. For example, an absolute improvement of 6.67% in terms of the mean accuracy is attained when the Fisher loss is used together with the domain adversarial loss on the Office-Home dataset.