TY  - JOUR
AU  - Adriana Romero
AU  - Petia Radeva
AU  - Carlo Gatta
PY  - 2015//
TI  - Meta-parameter free unsupervised sparse feature learning
T2  - TPAMI
JO  - IEEE Transactions on Pattern Analysis and Machine Intelligence
SP  - 1716
EP  - 1722
VL  - 37
IS  - 8
N2  - 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.
UR  - http://dx.doi.org/10.1109/TPAMI.2014.2366129
N1  - MILAB; 600.068; 600.079; 601.160
ID  - Adriana Romero2015
ER  -