Learning to Hash with Binary Deep Neural Network

TL;DR

This paper introduces a novel deep neural network architecture for binary hashing that directly outputs binary codes, addressing optimization challenges and incorporating properties like independence, balance, and similarity preservation, with promising experimental results.

Contribution

The work presents a new deep network design with direct binary code output and a novel optimization approach for binary hashing, improving upon previous methods.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively incorporates independence and balance constraints

Addresses non-smooth optimization challenges in binary hashing

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.