DocumentCode :
1764689
Title :
Locality-Constrained Sparse Auto-Encoder for Image Classification
Author :
Wei Luo ; Jian Yang ; Wei Xu ; Tao Fu
Author_Institution :
Sch. of Comput. Sci. & Eng., Nanjing Univ. of Sci. & Technol., Nanjing, China
Volume :
22
Issue :
8
fYear :
2015
fDate :
Aug. 2015
Firstpage :
1070
Lastpage :
1073
Abstract :
We propose a locality-constrained sparse auto-encoder (LSAE) for image classification in this letter. Previous work has shown that the locality is more essential than sparsity for classification task. We here introduce the concept of locality into the auto-encoder, which enables the auto-encoder to encode similar inputs using similar features. The proposed LSAE can be trained by the existing backprop algorithm; no complicated optimization is involved. Experiments on the CIFAR-10, STL-10 and Caltech-101 datasets validate the effectiveness of LSAE for classification task.
Keywords :
image classification; image coding; CIFAR-10 dataset; Caltech-101 dataset; LSAE; STL-10 data set; backprop algorithm; classification task; image classification; locality-constrained sparse auto-encoder; Decoding; Dictionaries; Encoding; Logistics; Optimization; Training; Uncertainty; Feature learning; image classification; sparse auto-encoder;
fLanguage :
English
Journal_Title :
Signal Processing Letters, IEEE
Publisher :
ieee
ISSN :
1070-9908
Type :
jour
DOI :
10.1109/LSP.2014.2384196
Filename :
6991568
Link To Document :
بازگشت