Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

This is a joint work by Behnam Gholami, Pritish Sahu, Ognjen Rudovic, Konstantinos Bousmalis, Vladimir Pavlovic

Abstract

Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target domains. Applying pairwise adaptation approaches to this setting may be suboptimal, as they fail to leverage shared information among multiple domains. In this work, we propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data. The resulting model, accompanied by an efficient optimization algorithm, allows simultaneous adaptation from a single source to multiple target domains. We test our approach on three challenging publicly-available datasets, showing that it outperforms several popular domain adaptation methods.

Full Paper: https://arxiv.org/abs/1810.11547

  • B. Gholami, P. Sahu, M. Kim, and V. Pavlovic, “Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation,” in IEEE International Conference on Computer Vision, ICCV, 6th Workshop on Transferring and Adapting Source Knowledge in Computer Vision, Seoul, Korea, 2019.
    [BibTeX]
    @inproceedings{gholami19iccvws,
    Address = {Seoul, Korea},
    Author = {Behnam Gholami and Pritish Sahu and Minyoung Kim and Vladimir Pavlovic},
    Booktitle = {{IEEE} International Conference on Computer Vision, {ICCV}, 6th Workshop on Transferring and Adapting Source Knowledge in Computer Vision},
    Date-Added = {2019-09-05 20:54:25 +0100},
    Date-Modified = {2019-09-05 20:57:09 +0100},
    Month = {October},
    Title = {Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation},
    Year = {2019}}

Leave a Reply

Your email address will not be published. Required fields are marked *