Meta-Parameter Free Unsupervised Sparse Feature Learning

@article{Romero2015MetaParameterFU,
  title={Meta-Parameter Free Unsupervised Sparse Feature Learning},
  author={Adriana Romero and Petia Radeva and Carlo Gatta},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2015},
  volume={37},
  pages={1716-1722}
}
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.