Radial Adaptive Node Embedding Hashing for cross-modal retrieval

Abstract

With the rapid growth of multimedia data on social networks, efficient and accurate cross-modal retrieval has become essential. Cross-modal hashing methods offer advantages such as fast retrieval speed and low storage cost. However, unsupervised deep cross-modal hashing methods often struggle with semantic misalignment and noise, limiting their effectiveness in capturing fine-grained relationships across modalities. To address these challenges, we propose Radial Adaptive Node Embedding Hashing (RANEH), designed to enhance semantic consistency and retrieval efficiency. Specifically, the semantic meta-similarity construction module reconstructs identity semantics using a similarity matrix, ensuring that hash codes retain modality-specific features. The radial adaptive hybrid coding method employs FastKAN as an encoder to map features into a shared hash space, maintaining semantic consistency across modalities. Lastly, the broadcasting node embedding unit leverages the Fast Kolmogorov–Arnold network to capture deep modality relationships, improving semantic alignment and node embedding accuracy. Experiments on the NUS-WIDE, MIRFlickr, and MSCOCO datasets show that RANEH method consistently outperforms state-of-the-art unsupervised cross-modal hashing methods in accuracy and efficiency. The codes are available at https://github.com/YunfeiChenMY/RANEH.