Proceedings of the 6th International Conference on Information Engineering for Mechanics and Materials

Multi-label Image Ranking based on Deep Convolutional Features

Authors
Guanghui Song, Xiaogang Jin, Genlang Chen, Yan Nie
Corresponding Author
Guanghui Song
Available Online November 2016.
DOI
https://doi.org/10.2991/icimm-16.2016.60How to use a DOI?
Keywords
feature learning, deep convolutional neural network, multi-label ranking
Abstract

Multi-label image ranking has many important applications in the real world, and it includes two core issues: image feature extraction approach and multi-label ranking algorithm. The existing works are mainly focused on the improvement of multi-label ranking algorithm based on the conventional visual features. Recently, image features extracted from the deep convolutional neural network have achieved impressive performance for a variety of vision tasks. Using these deep features as image representations have gained more and more attention on multi-label ranking problem. In this study, we evaluate the performance of the deep features using two baseline multi-label ranking algorithms. First, the deep convolutional neural network model pre-trained on ImageNet is fine-tuned to the target dataset. Second, the global deep features of raw image are extracted from the fine-tuned model and serve as the input data of ranking algorithms. Finally, experiments using the Tasmania Coral Point Count dataset demonstrate that the deep features enhance the expression ability in comparison with that of conventional visual features, and they can effectively improve multi-label ranking performance.

Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 6th International Conference on Information Engineering for Mechanics and Materials
Series
Advances in Engineering Research
Publication Date
November 2016
ISBN
978-94-6252-244-2
ISSN
2352-5401
DOI
https://doi.org/10.2991/icimm-16.2016.60How to use a DOI?
Copyright
© 2016, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Guanghui Song
AU  - Xiaogang Jin
AU  - Genlang Chen
AU  - Yan Nie
PY  - 2016/11
DA  - 2016/11
TI  - Multi-label Image Ranking based on Deep Convolutional Features
BT  - Proceedings of the 6th International Conference on Information Engineering for Mechanics and Materials
PB  - Atlantis Press
SP  - 324
EP  - 329
SN  - 2352-5401
UR  - https://doi.org/10.2991/icimm-16.2016.60
DO  - https://doi.org/10.2991/icimm-16.2016.60
ID  - Song2016/11
ER  -