Timezone: »

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
Alexey Dosovitskiy · Jost Tobias Springenberg · Martin Riedmiller · Thomas Brox

Thu Dec 11 11:00 AM -- 03:00 PM (PST) @ Level 2, room 210D

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).

Author Information

Alexey Dosovitskiy (University of Freiburg)
Jost Tobias Springenberg (University of Freiburg)
Martin Riedmiller (University of Freiburg)
Thomas Brox (University of Freiburg)

More from the Same Authors