The Community for Technology Leaders
Applications of Computer Vision, IEEE Workshop on (2013)
Clearwater Beach, FL, USA USA
Jan. 15, 2013 to Jan. 17, 2013
ISSN: 1550-5790
ISBN: 978-1-4673-5053-2
pp: 323-330
Fatemeh Mirrashed , University of Maryland, College Park
Vlad I. Morariu , University of Maryland, College Park
Behjat Siddiquie , SRI International
Rogerio S. Feris , IBM Research
Larry S. Davis , University of Maryland, College Park
We study the use of domain adaptation and transfer learning techniques as part of a framework for adaptive object detection. Unlike recent applications of domain adaptation work in computer vision, which generally focus on image classification, we explore the problem of extreme class imbalance present when performing domain adaptation for object detection. The main difficulty caused by this imbalance is that test images contain millions or billions of negative image subwindows but just a few image subwindows containing positive instances, which makes it difficult to adapt to changes in the positive classes present new domains by simple techniques such as random sampling. We propose an initial approach to addressing this problem and apply our technique to vehicle detection in a challenging urban surveillance dataset, demonstrating the performance of our approach with various amounts of supervision, including the fully unsupervised case.
Training, Principal component analysis, Cameras, Vehicles, Object detection, Kernel, Computational modeling

F. Mirrashed, V. I. Morariu, B. Siddiquie, R. S. Feris and L. S. Davis, "Domain adaptive object detection," Applications of Computer Vision, IEEE Workshop on(WACV), Clearwater Beach, FL, USA USA, 2013, pp. 323-330.
845 ms
(Ver 3.3 (11022016))