Method for training a compact discrete neural network descriptor

Abstract

Local patch descriptors are used in many computer vision tasks. Over the past decades, many methods of descriptor extraction were proposed. In recent years researchers have started to train descriptors via Convolutional Neural Networks (CNNs) which have shown their advantages in many other computer vision fields. However, the resulting descriptors are usually represented as a long real-valued vector. That leads to high computational complexity and memory usage in real applications with a large amount of data being processed. To deal with that problem binary local descriptors were designed, but they still have a large size. In this paper, we propose a method of discrete low-dimensional local descriptor creation with lightweight CNN. We show that for small-sized descriptors the quality drops significantly during simple binarization compared to floating-point ones. The experiments on HPatches dataset [1] demonstrate that our descretization approach dramatically outperforms the naive binarization for the compact descriptors.