NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval
This addresses the challenge of spatially-aware image retrieval for large datasets, offering flexibility and customization, though it appears incremental as it builds on existing neuro-symbolic and hashing methods.
The paper tackled the problem of customizable image retrieval with spatial awareness by introducing NeuroHash, a neuro-symbolic framework using Hyperdimensional Computing, which achieved superior performance on benchmark datasets with improved mAP@5K scores and a new spatial alignment metric.
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.