Low-Rank Sparse Coding for Image Classification

Published in ICCV 2013


In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information a-mong features in an image for the purpose of image-level
classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of codewords. As such, it
casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features
jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging bench-marks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing lo-cal features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding [36]


Tianzhu Zhang
Bernard Ghanem
Si Liu
Changsheng Xu
Narendra Ahuja

Paper (Pdf)
Paper (Bib)


This study is supported by the research grant for the Human Sixth Sense Program at the Advanced Digital Sciences Center from Singapore’s Agency for Science, Technology and Research (A*STAR).