Stretching Domain Adaptation: How far is too far?

TL;DR

This paper evaluates the limits of unsupervised domain adaptation across diverse modalities, introduces a new dataset suite for comprehensive testing, and proposes Deep MagNet, a novel network that achieves state-of-the-art results.

Contribution

It introduces a new dataset suite for cross-modality domain adaptation and proposes Deep MagNet, a network that significantly improves adaptation performance.

Findings

Deep MagNet achieves state-of-the-art results on benchmark datasets.

The new dataset suite reveals the limits of current domain adaptation methods.

Deep MagNet shows consistent improvements across diverse cross-modality tasks.

Abstract

While deep learning has led to significant advances in visual recognition over the past few years, such advances often require a lot of annotated data. Unsupervised domain adaptation has emerged as an alternative approach that does not require as much annotated data, prior evaluations of domain adaptation approaches have been limited to relatively similar datasets, e.g source and target domains are samples captured by different cameras. A new data suite is proposed that comprehensively evaluates cross-modality domain adaptation problems. This work pushes the limit of unsupervised domain adaptation through an in-depth evaluation of several state of the art methods on benchmark datasets and the new dataset suite. We also propose a new domain adaptation network called "Deep MagNet" that effectively transfers knowledge for cross-modality domain adaptation problems. Deep Magnet achieves state of the art performance on two benchmark datasets. More importantly, the proposed method shows consistent improvements in performance on the newly proposed dataset suite.