Title :
Meta-Parameter Free Unsupervised Sparse Feature Learning
Author :
Romero, Adriana ; Radeva, Petia ; Gatta, Carlo
Author_Institution :
Dept. of MAIA, Univ. de Barcelona, Barcelona, Spain
Abstract :
We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on CIFAR-10, STL-10 and UCMerced show that the method achieves the state-of-the-art performance, providing discriminative features that generalize well.
Keywords :
feature selection; unsupervised learning; CIFAR-10; STL-10; UCMerced; meta-parameter free; sparse visual feature; unsupervised sparse feature learning algorithm; Encoding; Niobium; Optimization; Sociology; Statistics; Training; Vectors; Representation learning; pre-training of deep networks; representation learning; sparse visual features; unsupervised feature learning;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2014.2366129
