Generic Object Detection with Dense Neural Patterns and Regionlets

Will Zou, Xiaoyu Wang, Miao Sun and Yuanqing Lin

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.72

Abstract

This paper addresses the challenge of establishing a bridge between deep convolutional neural networks and conventional object detection frameworks for accurate and efficient generic object detection. We introduce Dense Neural patterns, short for DNPs, which are dense local features derived from discriminatively trained deep convolutional neural networks. DNPs can be easily plugged into conventional detection frameworks in the same way as other dense local features(like HOG or LBP). The effectiveness of the proposed approach is demonstrated with the Regionlets object detection framework. It achieved 46.1\% mean average precision on the PASCAL VOC 2007 dataset, and 44.1\% on the PASCAL VOC 2010 dataset, which dramatically improves the original Regionlets approach without DNPs.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 314K)

Paper (PDF, 11 pages, 3.3M)

Bibtex File

Citation

Will Zou, Xiaoyu Wang, Miao Sun, and Yuanqing Lin. Generic Object Detection with Dense Neural Patterns and Regionlets. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.72
	title = {Generic Object Detection with Dense Neural Patterns and Regionlets},
	author = {Zou, Will and Wang, Xiaoyu and Sun, Miao and Lin, Yuanqing},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.72 }
}