2016/10/02 by Elad Hoffer, Hoffer, Elad, Itay Hubara +3 · 14 citations
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Artificial intelligence #Artificial neural network #Computer science #Convolutional neural network #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Pattern recognition (psychology) #Supervised learning #Unsupervised learning #cs.AI #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1610.00243
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2016/10/02 · arxiv created 2018/12/04 · arxiv updated 2018/12/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have been made to use unlabeled data to improve model performance by applying unsupervised techniques. These attempts require different architectures and training methods. In this work we present a novel approach for unsupervised training of Convolutional networks that is based on contrasting between spatial regions within images. This criterion can be employed within conventional neural networks and trained using standard techniques such as SGD and back-propagation, thus complementing supervised methods.