Leveraging High-Resolution Features for Improved Deep Hashing-based Image Retrieval

TL;DR

This paper introduces a novel deep hashing method using High-Resolution Networks (HRNets) as backbones, significantly improving image retrieval performance on complex datasets by leveraging high-resolution features.

Contribution

The study proposes the High-Resolution Hashing Network (HHNet) that utilizes HRNets for deep hashing, demonstrating superior results over traditional CNN-based methods on multiple benchmarks.

Findings

HHNet outperforms existing methods on all tested datasets.

High-resolution features are more effective for complex image retrieval tasks.

Optimal HRNet configurations enhance hashing performance.

Abstract

Deep hashing techniques have emerged as the predominant approach for efficient image retrieval. Traditionally, these methods utilize pre-trained convolutional neural networks (CNNs) such as AlexNet and VGG-16 as feature extractors. However, the increasing complexity of datasets poses challenges for these backbone architectures in capturing meaningful features essential for effective image retrieval. In this study, we explore the efficacy of employing high-resolution features learned through state-of-the-art techniques for image retrieval tasks. Specifically, we propose a novel methodology that utilizes High-Resolution Networks (HRNets) as the backbone for the deep hashing task, termed High-Resolution Hashing Network (HHNet). Our approach demonstrates superior performance compared to existing methods across all tested benchmark datasets, including CIFAR-10, NUS-WIDE, MS COCO, and ImageNet. This performance improvement is more pronounced for complex datasets, which highlights the need to learn high-resolution features for intricate image retrieval tasks. Furthermore, we conduct a comprehensive analysis of different HRNet configurations and provide insights into the optimal architecture for the deep hashing task