Deep Depth Domain Adaptation: A Case Study

Novi Patricia, Fabio M. Carlucci, Barbara Caputo; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2645-2650

Abstract


In the era of deep learning, many domain adaptation studies have been done on RGB images but not on depth. One of the reasons is that there are few databases available for researchers to explore domain shift on depth images. The contribution of this paper is to provide a benchmark to the community to study and evaluate deep domain adaptation methods on depth images, and compare the results with those obtained on the corresponding RGB data. We use two variants dataset that follow the settings from the first introduced RGB-D object dataset with 51 categories taken from multiple views. We also explore different colorization methods for depth images such as Colorjet and DE2CO. The experiments are conducted on several deep domain adaptation approaches on RGB and depth images. We understand that current deep DA methods can work well for RGB images but how to tackle the domain shift problem on depth images is still open questions.

Related Material


[pdf]
[bibtex]
@InProceedings{Patricia_2017_ICCV,
author = {Patricia, Novi and Carlucci, Fabio M. and Caputo, Barbara},
title = {Deep Depth Domain Adaptation: A Case Study },
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}