Product Sparse Coding
作者： Tiezheng Ge , Kaiming He , Jian Sun
关键词: Theoretical computer science 、 Image retrieval 、 Codebook 、 Product (mathematics) 、 Artificial intelligence 、 Neural coding 、 Algorithm 、 Time complexity 、 Computer science 、 Cartesian product 、 Contextual image classification 、 Sparse approximation
摘要: Sparse coding is a widely involved technique in computer vision. However, the expensive computational cost can hamper its applications, typically when codebook size must be limited due to concerns on running time. In this paper, we study special case of sparse which Cartesian product two subcodebooks. We present algorithms decompose problem into smaller subproblems, separately solved. Our solution, named as Product Coding (PSC), reduces time complexity from O(K) O(rK) K. practice, 20-100x faster than standard coding. experiments demonstrate efficiency and quality method applications image classification retrieval.
sci-hub.se 参考文章(32)
Herve Jegou, Matthijs Douze, Cordelia Schmid, Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search european conference on computer vision. ,vol. 5302, pp. 304- 317 ,(2008) , 10.1007/978-3-540-88682-2_24
Ken Chatfield, Victor Lempitsky, Andrea Vedaldi, Andrew Zisserman, The devil is in the details: an evaluation of recent feature encoding methods british machine vision conference. pp. 1- 12 ,(2011) , 10.5244/C.25.76
R. Arandjelovic, A. Zisserman, Three things everyone should know to improve object retrieval computer vision and pattern recognition. pp. 2911- 2918 ,(2012) , 10.1109/CVPR.2012.6248018
Herve Jegou, Florent Perronnin, Matthijs Douze, Jorge Sánchez, Patrick Perez, Cordelia Schmid, Aggregating Local Image Descriptors into Compact Codes IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 34, pp. 1704- 1716 ,(2012) , 10.1109/TPAMI.2011.235
A. Vedaldi, A. Zisserman, Sparse kernel approximations for efficient classification and detection computer vision and pattern recognition. pp. 2320- 2327 ,(2012) , 10.1109/CVPR.2012.6247943
Herve Jegou, Matthijs Douze, Cordelia Schmid, Patrick Perez, Aggregating local descriptors into a compact image representation computer vision and pattern recognition. pp. 3304- 3311 ,(2010) , 10.1109/CVPR.2010.5540039
Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, Thomas Huang, Yihong Gong, Locality-constrained Linear Coding for image classification computer vision and pattern recognition. pp. 3360- 3367 ,(2010) , 10.1109/CVPR.2010.5540018
Tiezheng Ge, Qifa Ke, Jian Sun, Sparse-Coded Features for Image Retrieval. british machine vision conference. ,(2013) , 10.5244/C.27.132
A. Babenko, V. Lempitsky, The inverted multi-index computer vision and pattern recognition. pp. 3069- 3076 ,(2012) , 10.1109/CVPR.2012.6248038
Jorge Sanchez, Florent Perronnin, High-dimensional signature compression for large-scale image classification CVPR 2011. pp. 1665- 1672 ,(2011) , 10.1109/CVPR.2011.5995504