Labelless Scene Classification with Semantic Matching
Meng Ye and Yuhong Guo
Abstract
Using high-level representation of images, e.g., objects and discriminative patches,
for scene classification has recently drawn increasing attention. Compared with low-level
image features, the high-level features carry rich semantic information that is useful for
improving semantic scene classification. Nevertheless, acquiring scene level annotations
remains a bottleneck for automatic scene classification, although plenty of related auxiliary resources such as images with object tags are free available on the Internet. In this
paper we propose a simple and novel methodology that exploits the rich auxiliary image
and text resources to perform labelless automatic scene classification without acquiring
training images annotated with scene labels. The key of our methodology is to utilize
existing object detectors to represent images in terms of high-level objects and then automatically categorize them based on the semantic relatedness of the object names and
scene labels. We further incorporate a label propagation step to refine the automatic scene
categorization results. Experiments are conducted on three standard scene classification
datasets.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.123
https://dx.doi.org/10.5244/C.31.123
Citation
Meng Ye and Yuhong Guo. Labelless Scene Classification with Semantic Matching. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 123.1-123.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_123,
title={Labelless Scene Classification with Semantic Matching},
author={Meng Ye and Yuhong Guo},
year={2017},
month={September},
pages={123.1-123.12},
articleno={123},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.123},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.123}
}