PT Journal
AU Adriana Romero
   Petia Radeva
   Carlo Gatta
TI Meta-parameter free unsupervised sparse feature learning
SO IEEE Transactions on Pattern Analysis and Machine Intelligence
JI TPAMI
PY 2015
BP 1716
EP 1722
VL 37
IS 8
DI 10.1109/TPAMI.2014.2366129
AB 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-theart performance, providing discriminative features that generalize well.
ER