Information Efficient Automatic Object Detection and Segmentation using Cosegmentation, Similarity based Clustering, and Graph Label Transfer

Johannes Steffen, Marko Rak, Tim König, Klaus-Dietz Tönnies

2016

Abstract

We tackle the problem of unsupervised object cosegmentation combining automatic image selection, cosegmentation, and knowledge transfer to yet unlabelled images. Furthermore, we overcome the limitations often present in state-of-the-art methods in object cosegmentation, namely, high complexity and poor scalability w.r.t. image set size. Our proposed approach is robust, reasonably fast, and scales linearly w.r.t. the image set size. We tested our approach on two commonly used cosegmentation data sets and outperformed some of the state-of-the-art methods using significantly less information than possible. Additionally, results indicate the applicability of our approach on larger image sets.

Download


Paper Citation


in Harvard Style

Steffen J., Rak M., König T. and Tönnies K. (2016). Information Efficient Automatic Object Detection and Segmentation using Cosegmentation, Similarity based Clustering, and Graph Label Transfer . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 397-406. DOI: 10.5220/0005625103970406

in Bibtex Style

@conference{icpram16,
author={Johannes Steffen and Marko Rak and Tim König and Klaus-Dietz Tönnies},
title={Information Efficient Automatic Object Detection and Segmentation using Cosegmentation, Similarity based Clustering, and Graph Label Transfer},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={397-406},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005625103970406},
isbn={978-989-758-173-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Information Efficient Automatic Object Detection and Segmentation using Cosegmentation, Similarity based Clustering, and Graph Label Transfer
SN - 978-989-758-173-1
AU - Steffen J.
AU - Rak M.
AU - König T.
AU - Tönnies K.
PY - 2016
SP - 397
EP - 406
DO - 10.5220/0005625103970406