Binary Constrained Deep Hashing Network For Image Retrieval Without Manual Annotation

Abstract

Learning compact binary codes for image retrieval task using deep neural networks has attracted increasing attention recently. However, training deep hashing networks for the task is challenging due to the binary constraints on the hash codes, the similarity preserving property, and the requirement for a vast amount of labelled images. To the best of our knowledge, none of the existing methods has tackled all of these challenges completely in a unified framework. In this work, we propose a novel end-to-end deep learning approach for the task, in which the network is trained to produce binary codes directly from image pixels without the need of manual annotation. In particular, to deal with the non-smoothness of binary constraints, we propose a novel pairwise constrained loss function, which simultaneously encodes the distances between pairs of hash codes, and the binary quantization error. In order to train the network with the proposed loss function, we propose an efficient parameter

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keydo2018binary

Related papers

• Compact Hash Code Learning With Binary Deep Neural Network (2017)9.03
• Supervised Hashing With End-to-end Binary Deep Neural Network (2017)2.26
• Learning To Hash With Binary Deep Neural Network (2016)14.93
• Simultaneous Feature Aggregating And Hashing For Compact Binary Code Learning (2019)9.92
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19
• HHF: Hashing-guided Hinge Function For Deep Hashing Retrieval (2021)14.24
• Simultaneous Region Localization And Hash Coding For Fine-grained Image Retrieval (2019)0.00
• Binary Generative Adversarial Networks For Image Retrieval (2017)18.34