Unsupervised Deep Hashing For Large-scale Visual Search

Abstract

Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes. In this paper, we propose a novel hashing approach based on unsupervised deep learning to hierarchically transform features into hash codes. Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes. Then, a Restricted Boltzmann Machine (RBM) layer with constraints is utilized to reduce the dimension in the hamming space. Extensive experiments on the problem of visual search demonstrate the competitiveness of our proposed approach compared to state-of-the-art.

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyxia2016unsupervised

Related papers

• Unsupervised Semantic Deep Hashing (2018)10.48
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40
• Supervised Hashing With End-to-end Binary Deep Neural Network (2017)2.26
• Deep Discrete Hashing With Self-supervised Pairwise Labels (2017)9.49
• Simultaneous Feature Aggregating And Hashing For Large-scale Image Search (2017)10.61
• Deep Supervised Discrete Hashing (2017)0.00
• Deep Residual Hashing (2016)0.00
• An Efficient Deep Learning Hashing Neural Network For Mobile Visual Search (2017)5.84