به نام خدا

Title: Domain Adaptive Object Detection

Authors: Fatemeh Mirrashed, Vlad I Morariu, Behjat Siddiquie, Rogerio S Feris, Larry S Davis

Abstract: 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 sub windows but just a few image sub windows containing positive instances, which makes it difficult to adapt to changes in the positive classes present new do-mains 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.   

Publish Year: 2013

Published in: WACV – IEEE

موضوع: بینایی ماشین (Computer Vision) – تشخیص اشیا (Object Detection)

مشاهده صفحه اول مقاله

دانلود مقاله

لینک مقاله در سایت ناشر

ایران سای – مرجع مقالات علمی فنی مهندسی

حامی دانش بومی ایرانیان