Abstract
We consider the problem of object classification by exploiting the hierarchy structure of object categories. Our proposed method first train a collection of binary classifiers to differentiate pairs of object categories at different levels of the object hierarchy. Then we use the outputs of these classifiers and the object hierarchy to define a new image representation. Our experimental results show that our proposed method outperforms other baseline methods on several image classification datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Li, L.J., Su, H., Xing, E.P., Fei-Fei, L.: Object bank: A high-level image representation for scene classification and semantic feature sparsification. In: Advances in Neural Information Processing Systems, MIT Press (2010)
Torresani, L., Szummer, M., Fitzgibbon, A.: Efficient object category recognition using classemes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 776–789. Springer, Heidelberg (2010)
Sadanand, S., Corso, J.J.: Action bank: A high-level representation of activity in video. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1234–1241. IEEE (2012)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Bengio, S., Weston, J., Grangier, D.: Label embedding trees for large multi-class tasks. In: Advances in Neural Information Processing Systems, pp. 163–171 (2010)
Deng, J., Satheesh, S., Berg, A.C., Li, F.: Fast and balanced: Efficient label tree learning for large scale object recognition. In: Advances in Neural Information Processing Systems, pp. 567–575 (2011)
Gao, T., Koller, D.: Discriminative learning of relaxed hierarchy for large-scale visual recognition. In: IEEE International Conference on Computer Vision (2011)
Sun, M., Huang, W., Savarese, S.: Finding the best path: an efficient and accurate classifier for image hierarchies. In: IEEE International Conference on Computer Vision (2013)
Deng, J., Berg, A.C., Fei-Fei, L.: Hierarchical semantic indexing for large scale image retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 785–792. IEEE (2011)
Deng, J., Krause, J., Berg, A.C., Fei-Fei, L.: Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3450–3457. IEEE (2012)
Cao, L., Gong, L., Kender, J.R., Codella, N.C., Smith, J.R.: Learning by focusing: A new framework for concept recognition and feature selection. In: IEEE International Conference on Multimedia and Expo, pp. 1–6. IEEE (2013)
Albaradei, S., Wang, Y., Cao, L., Li, J.: Learning mid-level features from object hierarchy for image classification. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision (2014)
Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 951–958. IEEE (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25, 1106–1114 (2012)
Yahoo research labs: Yahoo! shopping shoes image content (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Albaradei, S., Wang, Y. (2014). Object Classification Using a Semantic Hierarchy. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2014. Lecture Notes in Computer Science, vol 8887. Springer, Cham. https://doi.org/10.1007/978-3-319-14249-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-14249-4_22
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14248-7
Online ISBN: 978-3-319-14249-4
eBook Packages: Computer ScienceComputer Science (R0)