Deep Visual Domain Adaptation

TL;DR

This paper provides a comprehensive overview of deep visual domain adaptation methods, discussing architectures, recent trends, and potential improvements mainly for image classification and related tasks.

Contribution

It systematically reviews deep domain adaptation techniques in computer vision, highlighting recent trends and suggesting improvement strategies.

Findings

Comparison of different deep architecture exploitation methods

Overview of recent trends in deep visual DA

Discussion of orthogonal improvement strategies

Abstract

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade and the number of related work in the field exploded. The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. First, we detail and compared different possible ways of exploiting deep architectures for domain adaptation. Then, we propose an overview of recent trends in deep visual DA. Finally, we mention a few improvement strategies, orthogonal to these methods, that can be applied to these models. While we mainly focus on image classification, we give pointers to papers that extend these ideas for other applications such as semantic segmentation, object detection, person re-identifications, and others.