Abstract:
In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on w...Show MoreMetadata
Abstract:
In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on which the model is applied. Regardless of the cause, any distributional change that occurs after learning a classifier can degrade its performance at test time. Domain adaptation tries to mitigate this degradation. In this article, we provide a survey of domain adaptation methods for visual recognition. We discuss the merits and drawbacks of existing domain adaptation approaches and identify promising avenues for research in this rapidly evolving field.
Published in: IEEE Signal Processing Magazine ( Volume: 32, Issue: 3, May 2015)
University of Maryland at College Park, College Park, MD, US
Vishal M. Patel (pvishalm@umd.edu) received his B.S. degrees in electrical engineering and applied mathematics (with honors) and his M.S. degree in applied mathematics from North Carolina State University, Raleigh, in 2004 and 2005, respectively. He received his Ph.D. degree in electrical engineering from the University of Maryland, College Park, in 2010. He is a member of the research faculty at the University of Marylan...Show More
Vishal M. Patel (pvishalm@umd.edu) received his B.S. degrees in electrical engineering and applied mathematics (with honors) and his M.S. degree in applied mathematics from North Carolina State University, Raleigh, in 2004 and 2005, respectively. He received his Ph.D. degree in electrical engineering from the University of Maryland, College Park, in 2010. He is a member of the research faculty at the University of Marylan...View more
AT&T Labs-Research, Middletown, New Jersey 07748 United States
Raghuraman Gopalan (raghuram@research.att.com) received his Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is a senior member of technical staff at AT&T Labs–Research. His research interests are in computer vision and machine learning with a focus on object recognition problems. He is a Member of the IEEE.
Raghuraman Gopalan (raghuram@research.att.com) received his Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is a senior member of technical staff at AT&T Labs–Research. His research interests are in computer vision and machine learning with a focus on object recognition problems. He is a Member of the IEEE.View more
Harvard University, Cambridge, MA, US
Ruonan Li (ruonanLi@seas.harvard.edu) received his B.E. and M.E. degrees from Tsinghua University, Beijing, China. He received the Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is currently a research associate at Harvard University, Cambridge, Massachusetts. His research interests include general problems in computer vision, image processing, pattern recogn...Show More
Ruonan Li (ruonanLi@seas.harvard.edu) received his B.E. and M.E. degrees from Tsinghua University, Beijing, China. He received the Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is currently a research associate at Harvard University, Cambridge, Massachusetts. His research interests include general problems in computer vision, image processing, pattern recogn...View more
Department of Electrical and Electronic Engineering, Center for Automation Research, UMIACS, College Park, Maryland United States
Rama Chellappa (rama@umiacs.umd.edu) is a Minta Martin Professor of Engineering and the chair of the Electronics and Communication Engineering Department at the University of Maryland (UMD). He is a recipient of the K.S. Fu Prize from the International Association of Pattern Recognition, the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society, and the Technical Achievement...Show More
Rama Chellappa (rama@umiacs.umd.edu) is a Minta Martin Professor of Engineering and the chair of the Electronics and Communication Engineering Department at the University of Maryland (UMD). He is a recipient of the K.S. Fu Prize from the International Association of Pattern Recognition, the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society, and the Technical Achievement...View more
Contents University of Maryland at College Park, College Park, MD, US
Vishal M. Patel (pvishalm@umd.edu) received his B.S. degrees in electrical engineering and applied mathematics (with honors) and his M.S. degree in applied mathematics from North Carolina State University, Raleigh, in 2004 and 2005, respectively. He received his Ph.D. degree in electrical engineering from the University of Maryland, College Park, in 2010. He is a member of the research faculty at the University of Maryland Institute for Advanced Computer Studies. His research interests are in signal processing, computer vision, and machine learning with applications to imaging and biometrics. He was a recipient of the Oak Ridge Associated Universities postdoctoral fellowship in 2010. He is also a member of Eta Kappa Nu, Pi Mu Epsilon, and Phi Beta Kappa. He is a Member of the IEEE.
Vishal M. Patel (pvishalm@umd.edu) received his B.S. degrees in electrical engineering and applied mathematics (with honors) and his M.S. degree in applied mathematics from North Carolina State University, Raleigh, in 2004 and 2005, respectively. He received his Ph.D. degree in electrical engineering from the University of Maryland, College Park, in 2010. He is a member of the research faculty at the University of Maryland Institute for Advanced Computer Studies. His research interests are in signal processing, computer vision, and machine learning with applications to imaging and biometrics. He was a recipient of the Oak Ridge Associated Universities postdoctoral fellowship in 2010. He is also a member of Eta Kappa Nu, Pi Mu Epsilon, and Phi Beta Kappa. He is a Member of the IEEE.View more
AT&T Labs-Research, Middletown, New Jersey 07748 United States
Raghuraman Gopalan (raghuram@research.att.com) received his Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is a senior member of technical staff at AT&T Labs–Research. His research interests are in computer vision and machine learning with a focus on object recognition problems. He is a Member of the IEEE.
Raghuraman Gopalan (raghuram@research.att.com) received his Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is a senior member of technical staff at AT&T Labs–Research. His research interests are in computer vision and machine learning with a focus on object recognition problems. He is a Member of the IEEE.View more
Harvard University, Cambridge, MA, US
Ruonan Li (ruonanLi@seas.harvard.edu) received his B.E. and M.E. degrees from Tsinghua University, Beijing, China. He received the Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is currently a research associate at Harvard University, Cambridge, Massachusetts. His research interests include general problems in computer vision, image processing, pattern recognition, and machine learning with recent focuses on video analysis and video-based recognition, sociaLized visual analytics, cross-domain model adaptation, and the appLication of differential geometric methods to the related problems.
Ruonan Li (ruonanLi@seas.harvard.edu) received his B.E. and M.E. degrees from Tsinghua University, Beijing, China. He received the Ph.D. degree in electrical and computer engineering from the University of Maryland, College Park, in 2011. He is currently a research associate at Harvard University, Cambridge, Massachusetts. His research interests include general problems in computer vision, image processing, pattern recognition, and machine learning with recent focuses on video analysis and video-based recognition, sociaLized visual analytics, cross-domain model adaptation, and the appLication of differential geometric methods to the related problems.View more
Department of Electrical and Electronic Engineering, Center for Automation Research, UMIACS, College Park, Maryland United States
Rama Chellappa (rama@umiacs.umd.edu) is a Minta Martin Professor of Engineering and the chair of the Electronics and Communication Engineering Department at the University of Maryland (UMD). He is a recipient of the K.S. Fu Prize from the International Association of Pattern Recognition, the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society, and the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society. At UMD, he received college-and university-level recognition for research, teaching, innovation, and mentoring of undergraduate students. He is a fellow of the International Association of Pattern Recognition, the Optical Society of America, the American Association for the Advancement of Science, and the Association for Computing Machinery and holds four patents. He is a Fellow of the IEEE.
Rama Chellappa (rama@umiacs.umd.edu) is a Minta Martin Professor of Engineering and the chair of the Electronics and Communication Engineering Department at the University of Maryland (UMD). He is a recipient of the K.S. Fu Prize from the International Association of Pattern Recognition, the Society, Technical Achievement and Meritorious Service Awards from the IEEE Signal Processing Society, and the Technical Achievement and Meritorious Service Awards from the IEEE Computer Society. At UMD, he received college-and university-level recognition for research, teaching, innovation, and mentoring of undergraduate students. He is a fellow of the International Association of Pattern Recognition, the Optical Society of America, the American Association for the Advancement of Science, and the Association for Computing Machinery and holds four patents. He is a Fellow of the IEEE.View more
