Title :
segDeepM: Exploiting segmentation and context in deep neural networks for object detection
Author :
Yukun Zhu;Raquel Urtasun;Ruslan Salakhutdinov;Sanja Fidler
Author_Institution :
University of Toronto, Canada
fDate :
6/1/2015 12:00:00 AM
Abstract :
In this paper, we propose an approach that exploits object segmentation in order to improve the accuracy of object detection. We frame the problem as inference in a Markov Random Field, in which each detection hypothesis scores object appearance as well as contextual information using Convolutional Neural Networks, and allows the hypothesis to choose and score a segment out of a large pool of accurate object segmentation proposals. This enables the detector to incorporate additional evidence when it is available and thus results in more accurate detections. Our experiments show an improvement of 4.1% in mAP over the R-CNN baseline on PASCAL VOC 2010, and 3.4% over the current state-of-the-art, demonstrating the power of our approach.
Keywords :
"Image segmentation","Feature extraction","Proposals","Object detection","Detectors","Context modeling","Context"
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2015.7299102