Cookies

We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.


Durham Research Online
You are in:

Domain adaptation via image style transfer.

Atapour-Abarghouei, A. and Breckon, T.P. (2020) 'Domain adaptation via image style transfer.', in Domain adaptation in computer vision with deep learning. Cham: Springer, pp. 137-156.

Abstract

While recent growth in modern machine learning techniques has led to remarkable strides in computer vision applications, one of the most significant challenges facing learning-based vision systems is the scarcity of large, high-fidelity datasets required for training large-scale models. This has necessitated the creation of transfer learning and domain adaptation as a highly-active area of research, wherein the objective is to adapt a model trained on one set of data from a specific domain to perform well on previously-unseen data from a different domain. In this chapter, we use monocular depth estimation as a means of demonstrating a new perspective on domain adaptation. Most monocular depth estimation approaches either rely on large quantities of ground truth depth data, which is extremely expensive and difficult to obtain, or alternatively predict disparity as an intermediary step using a secondary supervisory signal leading to blurring and other artefacts. Training a depth estimation model using pixel-perfect synthetic depth images can resolve most of these issues but introduces the problem of domain shift from synthetic to real-world data. Here, we take advantage of recent advances in image style transfer and its connection with domain adaptation to predict depth from a single colour image based on training over a large corpus of synthetic data obtained from a virtual environment. Experimental results point to the impressive capabilities of style transfer used as a means of adapting the model to unseen data from a different domain.

Item Type:Book chapter
Full text:Publisher-imposed embargo until 19 August 2022.
(AM) Accepted Manuscript
File format - PDF
(2858Kb)
Status:Peer-reviewed
Publisher Web site:https://doi.org/10.1007/978-3-030-45529-3_8
Publisher statement:This is a post-peer-review, pre-copyedit version of a chapter published in Domain adaptation in computer vision with deep learning. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-45529-3_8
Date accepted:No date available
Date deposited:25 August 2020
Date of first online publication:19 August 2020
Date first made open access:19 August 2022

Save or Share this output

Export:
Export
Look up in GoogleScholar