CLIP Multi-modal Hashing for Multimedia Retrieval

TL;DR

This paper introduces CLIPMH, a multi-modal hashing method that leverages CLIP to extract and fuse text and vision features, significantly improving multimedia retrieval accuracy over existing methods.

Contribution

The paper presents a novel multi-modal hashing approach using CLIP for feature extraction and fusion, enhancing retrieval performance with large-scale pre-trained models.

Findings

Achieved up to 8.38% increase in mAP over state-of-the-art methods.

Demonstrated significant improvement in multi-modal hashing retrieval accuracy.

Validated effectiveness through extensive experiments.

Abstract

Multi-modal hashing methods are widely used in multimedia retrieval, which can fuse multi-source data to generate binary hash code. However, the individual backbone networks have limited feature expression capabilities and are not jointly pre-trained on large-scale unsupervised multi-modal data, resulting in low retrieval accuracy. To address this issue, we propose a novel CLIP Multi-modal Hashing (CLIPMH) method. Our method employs the CLIP framework to extract both text and vision features and then fuses them to generate hash code. Due to enhancement on each modal feature, our method has great improvement in the retrieval performance of multi-modal hashing methods. Compared with state-of-the-art unsupervised and supervised multi-modal hashing methods, experiments reveal that the proposed CLIPMH can significantly improve performance (a maximum increase of 8.38% in mAP).