Unsupervised Domain Expansion from Multiple Sources

05/26/2020
by   Jing Zhang, et al.
5

Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some applications. This problem is known as domain expansion. Unlike traditional domain adaptation in which the target domain is the domain defined by new data, in domain expansion the target domain is formed jointly by the source domains and the new domain (hence, domain expansion) and the label function to be learned must work for the expanded domain. Specifically, this paper presents a method for unsupervised multi-source domain expansion (UMSDE) where only the pre-learned models of the source domains and unlabelled new domain data are available. We propose to use the predicted class probability of the unlabelled data in the new domain produced by different source models to jointly mitigate the biases among domains, exploit the discriminative information in the new domain, and preserve the performance in the source domains. Experimental results on the VLCS, ImageCLEF_DA and PACS datasets have verified the effectiveness of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/14/2020

Multi-source Attention for Unsupervised Domain Adaptation

Domain adaptation considers the problem of generalising a model learnt u...
research
11/16/2017

Less-forgetful Learning for Domain Expansion in Deep Neural Networks

Expanding the domain that deep neural network has already learned withou...
research
12/21/2021

Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy

Determining causes of deaths (COD) occurred outside of civil registratio...
research
05/09/2021

Aggregating From Multiple Target-Shifted Sources

Multi-source domain adaptation aims at leveraging the knowledge from mul...
research
03/16/2020

Domain Adaptive Ensemble Learning

The problem of generalizing deep neural networks from multiple source do...
research
09/07/2018

Multi-Source Domain Adaptation with Mixture of Experts

We propose a mixture-of-experts approach for unsupervised domain adaptat...
research
04/19/2021

DANICE: Domain adaptation without forgetting in neural image compression

Neural image compression (NIC) is a new coding paradigm where coding cap...

Please sign up or login with your details

Forgot password? Click here to reset