Fast Discovery of Discriminative Mid-level Patches
Angran Lin, Xuhui Jia, Kowk Ping Chan
2015
Abstract
Learning discriminative mid-level patches has gained popularity in recent years since they can be applied to various computer vision topics and achieve better performance. However, state-of-the-art learning methods require a lot of training time, especially when the problem scale becomes much larger. In this paper we propose a simple but fast and effective way, the Fast Exemplar Clustering(FEC), to mine discriminative mid-level patches with only class labels provided. We verified our results on the task of scene classification and it took us only one day to train the model on the MIT Indoor 67 dataset using an Core i5 quad-core computer with Matlab. The results of our experiments revealed that the mid-level patches discovered by our method were semantically meaningful and achieved competitive accuracy compared to the state-of-the-art techniques. In addition, we created a new scene classification dataset named Outdoor Sight 20 which contains outdoor views of 20 famous tourist attractions to test our model.
DownloadPaper Citation
in Harvard Style
Lin A., Jia X. and Chan K. (2015). Fast Discovery of Discriminative Mid-level Patches . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-758-077-2, pages 53-61. DOI: 10.5220/0005183200530061
in Bibtex Style
@conference{icpram15,
author={Angran Lin and Xuhui Jia and Kowk Ping Chan},
title={Fast Discovery of Discriminative Mid-level Patches},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2015},
pages={53-61},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005183200530061},
isbn={978-989-758-077-2},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - Fast Discovery of Discriminative Mid-level Patches
SN - 978-989-758-077-2
AU - Lin A.
AU - Jia X.
AU - Chan K.
PY - 2015
SP - 53
EP - 61
DO - 10.5220/0005183200530061