A Survey on Deep Hashing Methods

Nearest neighbor search aims at obtaining the samples in database with smallest distances from them to queries, which is a basic task range of fields, including computer vision and data mining. Hashing one most widely used methods for its computational storage efficiency. With development deep learning, hashing show more advantages than traditional methods. In this survey, we detailedly investigate current algorithms supervised unsupervised hashing. Specifically, categorize into pairwise methods, ranking-based pointwise as well quantization according how measuring similarities learned hash codes. Moreover, categorized similarity reconstruction-based pseudo-label-based prediction-free self-supervised learning-based based on their semantic learning manners. We also introduce three related important topics semi-supervised hashing, domain adaption multi-modal Meanwhile, present some commonly public datasets scheme measure performance algorithms. Finally, discuss potential research directions conclusion.