Product Sparse Coding
CVPR(2014)
摘要
Sparse coding is a widely involved technique in computer vision. However, the expensive computational cost can hamper its applications, typically when the codebook size must be limited due to concerns on running time. In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks. We present algorithms to decompose this sparse coding problem into smaller subproblems, which can be separately solved. Our solution, named as Product Sparse Coding (PSC), reduces the time complexity from O(K) to O(&root;K) in the codebook size K. In practice, this can be 20-100x faster than standard sparse coding. In experiments we demonstrate the efficiency and quality of this method on the applications of image classification and image retrieval.
更多查看译文
关键词
image coding,time complexity,product sparse coding,vector quantization,cartesian product,psc,computational complexity,compressed sensing,image classification,codebook size,image retrieval,computer vision,vectors,encoding
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络