The Community for Technology Leaders
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Honolulu, Hawaii, USA
July 21, 2017 to July 26, 2017
ISSN: 1063-6919
ISBN: 978-1-5386-0457-1
pp: 6593-6601
ABSTRACT
Saliency detection aims to highlight the most relevant objects in an image. Methods using conventional models struggle whenever salient objects are pictured on top of a cluttered background while deep neural nets suffer from excess complexity and slow evaluation speeds. In this paper, we propose a simplified convolutional neural network which combines local and global information through a multi-resolution 4×5 grid structure. Instead of enforcing spacial coherence with a CRF or superpixels as is usually the case, we implemented a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary. We trained our model on the MSRA-B dataset, and tested it on six different saliency benchmark datasets. Results show that our method is on par with the state-of-the-art while reducing computation time by a factor of 18 to 100 times, enabling near real-time, high performance saliency detection.
INDEX TERMS
computer vision, feature extraction, image representation, image resolution, image segmentation, learning (artificial intelligence), neural nets, object detection
CITATION

Z. Luo, A. Mishra, A. Achkar, J. Eichel, S. Li and P. Jodoin, "Non-local Deep Features for Salient Object Detection," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, 2017, pp. 6593-6601.
doi:10.1109/CVPR.2017.698
669 ms
(Ver 3.3 (11022016))