Home
Uni-Logo
 

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

Alexey Dosovitskiy, J. Springenberg, M. Riedmiller, Thomas Brox
Advances in Neural Information Processing Systems 27 (NIPS), 2014
Abstract: Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training. In this paper we present an approach for training a convolutional neural network using only unlabeled data. We train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sampled ’seed’ image patch. We find that this simple feature learning algorithm is surprisingly successful when applied to visual object recognition. The feature representation learned by our algorithm achieves classification results matching or outperforming the current state-of-the-art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101).
Downloads

Other associated files : exemplar_CNN.pdf [407KB]   exemplar_CNN_supp.pdf [171KB]  

Images and movies

 

BibTex reference

@InProceedings{DB14b,
  author       = "A.Dosovitskiy and J.T.Springenberg and M.Riedmiller and T.Brox",
  title        = "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks",
  booktitle    = "Advances in Neural Information Processing Systems 27 (NIPS)",
  year         = "2014",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2014/DB14b"
}

Other publications in the database