Unsupervised feature learning by augmenting single images

Abstract

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).

ICLR 2014 workshop track submission (7 pages, 4 figures, 1 table)

References in corpus (2)

• Rich feature hierarchies for accurate object detection and semantic segmentation
• Visualizing and Understanding Convolutional Networks

Cited by in corpus (4)

• Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
• Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification
• Domain-Size Pooling in Local Descriptors: DSP-SIFT
• Committees of deep feedforward networks trained with few data