Fusion Hashing: A General Framework for Self-improvement of Hashing

TL;DR

Fusion Hashing (FH) is a versatile framework that enhances existing hashing methods by combining multiple hash codes through novel fusion strategies, leading to improved accuracy without significant additional costs.

Contribution

The paper introduces a general framework for self-improvement of hashing methods by fusing multiple hash codes, avoiding new constraints and achieving better precision.

Findings

Fusion Hashing improves accuracy of existing methods.

The framework is applicable to various hashing algorithms.

Experimental results show superior performance on benchmark datasets.

Abstract

Hashing has been widely used for efficient similarity search based on its query and storage efficiency. To obtain better precision, most studies focus on designing different objective functions with different constraints or penalty terms that consider neighborhood information. In this paper, in contrast to existing hashing methods, we propose a novel generalized framework called fusion hashing (FH) to improve the precision of existing hashing methods without adding new constraints or penalty terms. In the proposed FH, given an existing hashing method, we first execute it several times to get several different hash codes for a set of training samples. We then propose two novel fusion strategies that combine these different hash codes into one set of final hash codes. Based on the final hash codes, we learn a simple linear hash function for the samples that can significantly improve model precision. In general, the proposed FH can be adopted in existing hashing method and achieve more precise and stable performance compared to the original hashing method with little extra expenditure in terms of time and space. Extensive experiments were performed based on three benchmark datasets and the results demonstrate the superior performance of the proposed framework