Low-Rank Sparse Coding for Image Classification

Tianzhu Zhang, Bernard Ghanem, Si Liu, Changsheng Xu, Narendra Ahuja

Research output: Chapter in Book/Report/Conference proceedingConference contribution

106 Scopus citations

Abstract

In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among 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 code words. 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 benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local 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.
Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Computer Vision
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages281-288
Number of pages8
ISBN (Print)9781479928408
DOIs
StatePublished - Mar 7 2014

Fingerprint Dive into the research topics of 'Low-Rank Sparse Coding for Image Classification'. Together they form a unique fingerprint.

Cite this