NeuroHash：一种用于空间感知图像哈希与检索的超维神经符号框架
NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval
AI总结：
NeuroHash利用超维计算结合深度神经网络，实现空间感知的可定制图像哈希检索，在基准数据集上优于现有方法。
摘要：
从大型数据集中进行可定制的图像检索仍然是一个关键挑战，尤其是在保留图像内部空间关系方面。传统的哈希方法主要基于深度学习，往往无法充分捕获空间信息且缺乏透明度。在本文中，我们介绍了NeuroHash，一种新颖的神经符号框架，利用超维计算（HDC）实现高度可定制、空间感知的图像检索。NeuroHash将预训练的深度神经网络模型与基于HDC的符号模型相结合，允许灵活操作哈希值以支持条件图像检索。我们的方法包括一个自监督的上下文感知HDC编码器，以及用于使用多线性超平面优化低维双极哈希的新颖损失项。我们在两个基准数据集上评估了NeuroHash，展示了相较于最先进的哈希方法更优的性能，通过mAP@5K分数和我们新引入的度量mAP@5Kr（用于评估空间对齐）来衡量。结果突显了NeuroHash在实现竞争性能的同时，在灵活性和定制性方面提供显著优势的能力，为更先进和多功能的图像检索系统铺平了道路。
英文摘要：
Customizable image retrieval from large datasets remains a critical challenge, particularly when preserving spatial relationships within images. Traditional hashing methods, primarily based on deep learning, often fail to capture spatial information adequately and lack transparency. In this paper, we introduce NeuroHash, a novel neuro-symbolic framework leveraging Hyperdimensional Computing (HDC) to enable highly customizable, spatially-aware image retrieval. NeuroHash combines pre-trained deep neural network models with HDC-based symbolic models, allowing for flexible manipulation of hash values to support conditional image retrieval. Our method includes a self-supervised context-aware HDC encoder and novel loss terms for optimizing lower-dimensional bipolar hashing using multilinear hyperplanes. We evaluate NeuroHash on two benchmark datasets, demonstrating superior performance compared to state-of-the-art hashing methods, as measured by mAP@5K scores and our newly introduced metric, mAP@5Kr, which assesses spatial alignment. The results highlight NeuroHash's ability to achieve competitive performance while offering significant advantages in flexibility and customization, paving the way for more advanced and versatile image retrieval systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
