2013/01/14 by Christian Osendorfer, Justin Bayer, Osendorfer, Christian +5
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1301.2840
openalex publication_date 2013/01/14 · arxiv created 2013/04/25 · arxiv updated 2013/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision. Using a large amount of unlabeled data, unsupervised feature learning methods are utilized to construct high-level representations that are discriminative enough for subsequently trained supervised classification algorithms. However, it has never been quantitatively investigated yet how well unsupervised learning methods can find low-level representations for image patches without any additional supervision. In this paper we examine the performance of pure unsupervised methods on a low-level correspondence task, a problem that is central to many Computer Vision applications. We find that a special type of Restricted Boltzmann Machines (RBMs) performs comparably to hand-crafted descriptors. Additionally, a simple binarization scheme produces compact representations that perform better than several state-of-the-art descriptors.