Learning To Hash With Binary Deep Neural Network

Abstract

This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art.

Stats

• citations97
• S2 citations—
• github stars0
• HF likes0
• heat score14.93
• arxiv keydo2016learning

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
• Binary Constrained Deep Hashing Network For Image Retrieval Without Manual Annotation (2018)5.84
• Embarrassingly Simple Binary Representation Learning (2019)9.41
• Dual Asymmetric Deep Hashing Learning (2018)9.03
• From Hashing To Cnns: Training Binaryweight Networks Via Hashing (2018)12.40
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19