Linear spatial pyramid matching using sparse coding for image classification
Jianchao Yang, Kai Yu, Yihong Gong et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2009
Recently SVMs using spatial pyramid matching (SPM) kernel have been highly successful in image classification. Despite its popularity, these nonlinear SVMs have a complexity O(n2∼ n3) in training and O(n) in testing, where n is the training size, implying that it is nontrivial to scaleup the algorithms to handlemore than thousands of training images. In this paper we develop an extension of the SPM method, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and propose a linear SPM kernel based on SIFT sparse codes. This new approach remarkably reduces the complexity of SVMs to O(n) in training and a constant in testing. In a number of image categorization experiments, we find that, in terms of classification accuracy, the suggested linear SPM based on sparse coding of SIFT descriptors always significantly outperforms the linear SPM kernel on histograms, and is even better than the nonlinear SPM kernels, leading to state-of-the-art performance on several benchmarks by using a single type of descriptors.
Cited by 2,828 works. doi:10.1109/cvpr.2009.5206757
Authors
References
- LIBSVM
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
- Caltech-256 Object Category Dataset
- Libsvm : A library for support vector machines
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
- Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
- A Bayesian Hierarchical Model for Learning Natural Scene Categories
- Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
- Efficient sparse coding algorithms