Neurohash: A Hyperdimensional Neuro-symbolic Framework For Spatially-aware Image Hashing And Retrieval

Abstract

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,

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyun2024neurohash

Related papers

• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
• Metric-learning Based Deep Hashing Network For Content Based Retrieval Of Remote Sensing Images (2019)13.93
• Leveraging High-resolution Features For Improved Deep Hashing-based Image Retrieval (2024)4.52
• Hybridhash: Hybrid Convolutional And Self-attention Deep Hashing For Image Retrieval (2024)12.56
• Deep Semantic Multimodal Hashing Network For Scalable Image-text And Video-text Retrievals (2019)14.43
• Unsupervised Semantic Deep Hashing (2018)10.48
• SSDH: Semi-supervised Deep Hashing For Large Scale Image Retrieval (2016)15.40