Zero-Shot Deep Domain Adaptation release_4zl3hiiegjbtxjh523de4xn6dq

by Kuan-Chuan Peng, Ziyan Wu, Jan Ernst

Released as a article .

2018  

Abstract

Domain adaptation is an important tool to transfer knowledge about a task (e.g. classification) learned in a source domain to a second, or target domain. Current approaches assume that task-relevant target-domain data is available during training. We demonstrate how to perform domain adaptation when no such task-relevant target-domain data is available. To tackle this issue, we propose zero-shot deep domain adaptation (ZDDA), which uses privileged information from task-irrelevant dual-domain pairs. ZDDA learns a source-domain representation which is not only tailored for the task of interest but also close to the target-domain representation. Therefore, the source-domain task of interest solution (e.g. a classifier for classification tasks) which is jointly trained with the source-domain representation can be applicable to both the source and target representations. Using the MNIST, Fashion-MNIST, NIST, EMNIST, and SUN RGB-D datasets, we show that ZDDA can perform domain adaptation in classification tasks without access to task-relevant target-domain training data. We also extend ZDDA to perform sensor fusion in the SUN RGB-D scene classification task by simulating task-relevant target-domain representations with task-relevant source-domain data. To the best of our knowledge, ZDDA is the first domain adaptation and sensor fusion method which requires no task-relevant target-domain data. The underlying principle is not particular to computer vision data, but should be extensible to other domains.
In text/plain format

Archived Files and Locations

application/pdf  2.2 MB
file_h5olpzrmizc6hixvek5hhpj4pa
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-07-24
Version   v5
Language   en ?
arXiv  1707.01922v5
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 4f852f0b-6272-4170-87b5-5ffa07977070
API URL: JSON