Unsupervised feature learning by augmenting single images
This work addresses the problem of reducing labeling costs in computer vision by proposing an unsupervised method, though it is incremental as it builds on existing data augmentation techniques.
The paper tackled unsupervised feature learning by using data augmentation to create surrogate classes from single image patches, and found that this simple method achieved competitive classification results on STL-10, CIFAR-10, and Caltech-101 datasets.
When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In this paper we investigate if it is possible to use data augmentation as the main component of an unsupervised feature learning architecture. To that end we sample a set of random image patches and declare each of them to be a separate single-image surrogate class. We then extend these trivial one-element classes by applying a variety of transformations to the initial 'seed' patches. Finally we train a convolutional neural network to discriminate between these surrogate classes. The feature representation learned by the network can then be used in various vision tasks. We find that this simple feature learning algorithm is surprisingly successful, achieving competitive classification results on several popular vision datasets (STL-10, CIFAR-10, Caltech-101).