Deep Visual Domain Adaptation: A Survey

TL;DR

This survey reviews deep learning-based domain adaptation techniques in computer vision, categorizing methods, analyzing their approaches, and discussing applications and future challenges in the field.

Contribution

It provides a comprehensive taxonomy, summarizes recent methods, and discusses applications and future directions in deep visual domain adaptation.

Findings

Deep domain adaptation methods improve transferability of features.

Categorization of methods based on training loss.

Identification of challenges and future research directions.

Abstract

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaption methods leverage deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning. There have been comprehensive surveys for shallow domain adaption, but few timely reviews the emerging deep learning based methods. In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions. First, we present a taxonomy of different deep domain adaption scenarios according to the properties of data that define how two domains are diverged. Second, we summarize deep domain adaption approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories. Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection. Fourth, some potential deficiencies of current methods and several future directions are highlighted.