Online dictionary learning for Local Coordinate Coding with Locality Coding Adaptors

• Published in: Neurocomputing (Amsterdam) Vol. 157; pp. 61 - 69
• Main Authors: Pang, Junbiao, Zhang, Chunjie, Qin, Lei, Zhang, Weigang, Qing, Laiyun, Huang, Qingming, Yin, Baocai
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2015
• Subjects: Large scale problem; Local Coordinate Coding; Locality Coding Adaptor; Online training; Surrogate function; Locality Coding Adaptor; Surrogate function; Large scale problem; Online training; Local Coordinate Coding
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2015.01.035

Dictionary in Local Coordinate Coding (LCC) is important to approximate a non-linear function with linear ones. Optimizing dictionary from predefined coding schemes is a challenge task. This paper focuses on learning dictionary from two Locality Coding Adaptors (LCAs), i.e., locality Gaussian Adaptor (GA) and locality Euclidean Adaptor (EA), for large-scale and high-dimension datasets. Online dictionary learning is formulated as two cycling steps, local coding and dictionary updating. Both stages scale up gracefully to large-scale datasets with millions of data. The experiments on different applications demonstrate that our method leads to a faster dictionary learning than the classical ones or the state-of-the-art methods.