Tackling unsupervised multi-source domain adaptation with optimism and consistency

09/29/2020
by   Diogo Pernes, et al.
0

It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to adjust the mixture distribution weights remains an open question. Moreover, most existing work on this topic focuses only on minimizing the error on the source domains and achieving domain-invariant representations, which is insufficient to ensure low error on the target domain. In this work, we present a novel framework that addresses both problems and beats the current state of the art by using a mildly optimistic objective function and consistency regularization on the target samples.

READ FULL TEXT

page 13

page 17

research
03/29/2020

Mutual Learning Network for Multi-Source Domain Adaptation

Early Unsupervised Domain Adaptation (UDA) methods have mostly assumed t...
research
09/11/2019

Domain Aggregation Networks for Multi-Source Domain Adaptation

In many real-world applications, we want to exploit multiple source data...
research
09/16/2020

Transformer Based Multi-Source Domain Adaptation

In practical machine learning settings, the data on which a model must m...
research
08/16/2019

Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning

Supervised learning algorithms trained on medical images will often fail...
research
01/13/2020

Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

Domain adaptation performance of a learning algorithm on a target domain...
research
04/27/2022

Attention Consistency on Visual Corruptions for Single-Source Domain Generalization

Generalizing visual recognition models trained on a single distribution ...
research
03/21/2016

Beyond Sharing Weights for Deep Domain Adaptation

The performance of a classifier trained on data coming from a specific d...

Please sign up or login with your details

Forgot password? Click here to reset