Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation

02/19/2020
by   Hai H. Tran, et al.
0

In this paper, we study the problem of unsupervised domain adaptation that aims at obtaining a prediction model for the target domain using labeled data from the source domain and unlabeled data from the target domain. There exists an array of recent research based on the idea of extracting features that are not only invariant for both domains but also provide high discriminative power for the target domain. In this paper, we propose an idea of empowering the discriminativeness: Adding a new, artificial class and training the model on the data together with the GAN-generated samples of the new class. The trained model based on the new class samples is capable of extracting the features that are more discriminative by repositioning data of current classes in the target domain and therefore drawing the decision boundaries more effectively. Our idea is highly generic so that it is compatible with many existing methods such as DANN, VADA, and DIRT-T. We conduct various experiments for the standard data commonly used for the evaluation of unsupervised domain adaptations and demonstrate that our algorithm achieves the SOTA performance for many scenarios.

READ FULL TEXT

page 7

page 14

research
03/24/2019

Cluster Alignment with a Teacher for Unsupervised Domain Adaptation

Deep learning methods have shown promise in unsupervised domain adaptati...
research
05/22/2019

Simplified Neural Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) is the task of modifying a statisti...
research
03/17/2023

Diffusion-based Target Sampler for Unsupervised Domain Adaptation

Limited transferability hinders the performance of deep learning models ...
research
06/27/2012

Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation

We study the problem of unsupervised domain adaptation, which aims to ad...
research
05/02/2023

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

We study the problem of choosing algorithm hyper-parameters in unsupervi...
research
11/20/2017

Parameter Reference Loss for Unsupervised Domain Adaptation

The success of deep learning in computer vision is mainly attributed to ...
research
03/26/2020

Unsupervised domain adaptation with exploring more statistics and discriminative information

Unsupervised domain adaptation aims at transferring knowledge from the l...

Please sign up or login with your details

Forgot password? Click here to reset