Learning Object-to-Class Kernels for Scene Classification
- 4 June 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (8), 3241-3253
- https://doi.org/10.1109/tip.2014.2328894
Abstract
High-level image representations have drawn increasing attention in visual recognition, e.g., scene classification, since the invention of the object bank. The object bank represents an image as a response map of a large number of pretrained object detectors and has achieved superior performance for visual recognition. In this paper, based on the object bank representation, we propose the object-to-class (O2C) distances to model scene images. In particular, four variants of O2C distances are presented, and with the O2C distances, we can represent the images using the object bank by lower-dimensional but more discriminative spaces, called distance spaces, which are spanned by the O2C distances. Due to the explicit computation of O2C distances based on the object bank, the obtained representations can possess more semantic meanings. To combine the discriminant ability of the O2C distances to all scene classes, we further propose to kernalize the distance representation for the final classification. We have conducted extensive experiments on four benchmark data sets, UIUC-Sports, Scene-15, MIT Indoor, and Caltech-101, which demonstrate that the proposed approaches can significantly improve the original object bank approach and achieve the state-of-the-art performance.Keywords
Funding Information
- Support Plan of Young Teachers of Heilongjiang Province
- Harbin Engineering University, Harbin, China (1155G17)
This publication has 36 references indexed in Scilit:
- Local Naive Bayes Nearest Neighbor for image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- The NBNN kernelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Lexical Frequency Profiles and Zipf's LawLanguage Learning, 2011
- Object Detection with Discriminatively Trained Part-Based ModelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- In defense of Nearest-Neighbor based image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- Semantic Modeling of Natural Scenes for Content-Based Image RetrievalInternational Journal of Computer Vision, 2006
- Automatic photo pop-upACM Transactions on Graphics, 2005
- Learning multi-label scene classificationPattern Recognition, 2004
- Meaning in Visual SearchScience, 1975