# NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval

arXiv: https://arxiv.org/abs/2404.11025 · HTML: https://mlsanity.com/paper/2404.11025/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 18 of 18)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Central Similarity Quantization for Efficient Image and Video Retrieval](https://mlsanity.com/paper/1908.00347/) (2019)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [GraphHD: Efficient graph classification using hyperdimensional computing](https://mlsanity.com/paper/2205.07826/) (2022)
- [DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs](https://mlsanity.com/paper/1905.03465/) (2019)
- [Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2002.11930/) (2020)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Binary Generative Adversarial Networks for Image Retrieval](https://mlsanity.com/paper/1708.04150/) (2017)
- [Stochastic Generative Hashing](https://mlsanity.com/paper/1701.02815/) (2017)
- [LeHDC: Learning-Based Hyperdimensional Computing Classifier](https://mlsanity.com/paper/2203.09680/) (2022)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval](https://mlsanity.com/paper/2401.07212/) (2024)
- [Learning to Hash Naturally Sorts](https://mlsanity.com/paper/2201.13322/) (2022)

## Built on by (most cited first, 6 of 6)

- [DecoHD: Decomposed Hyperdimensional Classification under Extreme Memory Budgets](https://mlsanity.com/paper/2511.03911/) (2025)
- [LogHD: Robust Compression of Hyperdimensional Classifiers via Logarithmic Class-Axis Reduction](https://mlsanity.com/paper/2511.03938/) (2025)
- [Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective](https://mlsanity.com/paper/2603.03830/) (2026)
- [Exploiting Boosting in Hyperdimensional Computing for Enhanced Reliability in Healthcare](https://mlsanity.com/paper/2411.14612/) (2024)
- [Federated Hyperdimensional Computing for Resource-Constrained Industrial IoT](https://mlsanity.com/paper/2603.20037/) (2026)
- [Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding](https://mlsanity.com/paper/2607.11936/) (2026)

## Abstract (arXiv)

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.