CLIP Multi-modal Hashing: A new baseline CLIPMH

TL;DR

This paper introduces CLIPMH, a multi-modal hashing method leveraging CLIP to extract and fuse image and text features, significantly improving retrieval accuracy over existing methods by enhancing feature expressiveness.

Contribution

The paper proposes a new baseline CLIPMH that uses CLIP for feature extraction and fusion, addressing low accuracy issues in multi-modal hashing.

Findings

CLIPMH outperforms state-of-the-art methods with up to 8.38% accuracy increase.

CLIP enhances feature expressiveness for better retrieval performance.

The method demonstrates significant improvements over traditional backbone networks.

Abstract

The multi-modal hashing method is widely used in multimedia retrieval. It can fuse multi-source data to generate binary hash code. However, the current multi-modal methods have the problem of low retrieval accuracy. The reason is that the individual backbone networks have limited feature expression capabilities and are not jointly pre-trained on large-scale unsupervised multi-modal data. To solve this problem, we propose a new baseline CLIP Multi-modal Hashing (CLIPMH) method. It uses CLIP model to extract text and image features, and then fuse to generate hash code. CLIP improves the expressiveness of each modal feature. In this way, it can greatly improve the retrieval performance of multi-modal hashing methods. In comparison to state-of-the-art unsupervised and supervised multi-modal hashing methods, experiments reveal that the proposed CLIPMH can significantly enhance performance (Maximum increase of 8.38%). CLIP also has great advantages over the text and visual backbone networks commonly used before.