Discriminative Unsupervised Feature Learning with Convolutional Neural Networks
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).
Cite
Text
Dosovitskiy et al. "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks." Neural Information Processing Systems, 2014.Markdown
[Dosovitskiy et al. "Discriminative Unsupervised Feature Learning with Convolutional Neural Networks." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/dosovitskiy2014neurips-discriminative/)BibTeX
@inproceedings{dosovitskiy2014neurips-discriminative,
title = {{Discriminative Unsupervised Feature Learning with Convolutional Neural Networks}},
author = {Dosovitskiy, Alexey and Springenberg, Jost Tobias and Riedmiller, Martin and Brox, Thomas},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {766-774},
url = {https://mlanthology.org/neurips/2014/dosovitskiy2014neurips-discriminative/}
}