Fisher Deep Domain Adaptation

by   Yinghua Zhang, et al.

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 mean accuracy is attained when the Fisher loss is used together with the domain adversarial loss on the Office-Home dataset.


page 1

page 2

page 3

page 4


Class Conditional Alignment for Partial Domain Adaptation

Adversarial adaptation models have demonstrated significant progress tow...

Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images

Automatic and accurate Gleason grading of histopathology tissue slides i...

DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains

In astronomy, neural networks are often trained on simulation data with ...

Loss-based Sequential Learning for Active Domain Adaptation

Active domain adaptation (ADA) studies have mainly addressed query selec...

MetaSID: Singer Identification with Domain Adaptation for Metaverse

Metaverse has stretched the real world into unlimited space. There will ...

Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

Domain adaptation is to transfer the shared knowledge learned from the s...

SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning

As learning-based approaches progress towards automating robot controlle...

1 Introduction