Advanced Methods and Deep Learning in Computer Vision

Chapter 7: Unsupervised domain adaptation using shallow and deep representations

Yogesh Balaji^a; Hien Nguyen^b; Rama Chellappa^c    aDepartment of Computer Science and UMACS, University of Maryland, College Park, MD, United States^bDepartment of Electrical and Computer Engineering, University of Houston, Houston, TX, United States^cDepartments of Electrical and Computer Engineering and Biomedical Engineering, Johns Hopkins University, Baltimore, MD, United States

Abstract

The inputs to a computer vision system often contain novel variations owing to the diverse operating conditions in the external world. Machine learning models fail to generalize to such variations, and this raises reliability concerns especially in safety-critical applications such ...