Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

TL;DR

This paper introduces an unsupervised method for training convolutional neural networks to learn generic, transformation-robust features by discriminating surrogate classes, outperforming previous methods on several datasets and excelling in geometric matching tasks.

Contribution

It presents a novel unsupervised training approach for CNNs that learns generic features by discriminating surrogate classes formed through transformations, reducing reliance on labeled data.

Findings

Outperforms state-of-the-art in unsupervised learning on multiple datasets

Produces features robust to transformations for various tasks

Outperforms SIFT in geometric matching scenarios

Abstract

Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning paradigm, where sufficiently many input-output pairs are required for training. Acquisition of large training sets is one of the key challenges, when approaching a new task. In this paper, we aim for generic feature learning and present an approach for training a convolutional network using only unlabeled data. To this end, 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. In contrast to supervised network training, the resulting feature representation is not class specific. It rather provides robustness to the transformations that have been applied during training. This generic feature representation allows for classification results that outperform the state of the art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101, Caltech-256). While such generic features cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.