How good are detection proposals, really?
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.24
Abstract
Abstract Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despite the popularity of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in depth analysis of eight object proposal methods along with four baselines regarding ground truth annotation recall (on Pascal VOC 2007 and ImageNet 2013), repeatability, and impact on DPM detector performance. Our findings show common weaknesses of existing methods, and provide insights to choose the most adequate method for different settings.
Session
Segmentation and Object Detection
Files
Extended Abstract (PDF, 1 page, 537K)Paper (PDF, 12 pages, 1.6M)
Supplemental Materials (ZIP, 2.3M)
Bibtex File
Presentation
Citation
Jan Hosang, Rodrigo Benenson, and Bernt Schiele. How good are detection proposals, really?. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.24
title = {How good are detection proposals, really?},
author = {Hosang, Jan and Benenson, Rodrigo and Schiele, Bernt},
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.28.24 }
}