FDDH: Fast Discriminative Discrete Hashing For Large-scale Cross-modal Retrieval

Abstract

Cross-modal hashing, favored for its effectiveness and efficiency, has received wide attention to facilitating efficient retrieval across different modalities. Nevertheless, most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes, while often involving time-consuming training procedure for handling the large-scale dataset. To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval. More specifically, FDDH introduces an orthogonal basis to regress the targeted hash codes of training examples to their corresponding semantic labels, and utilizes "-dragging technique to provide provable large semantic margins. Accordingly, the discriminative power of

Stats

• citations62
• S2 citations—
• github stars9
• HF likes0
• heat score15.50
• arxiv keyliu2021fddh

Related papers

• Efficient Discrete Supervised Hashing For Large-scale Cross-modal Retrieval (2019)11.08
• Discriminative Supervised Hashing For Cross-modal Similarity Search (2018)7.81
• Fusion-supervised Deep Cross-modal Hashing (2019)8.60
• Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
• MTFH: A Matrix Tri-factorization Hashing Framework For Efficient Cross-modal Retrieval (2018)16.88
• Weakly-paired Cross-modal Hashing (2019)0.00
• Deep Class-guided Hashing For Multi-label Cross-modal Retrieval (2024)6.20
• Correlation Hashing Network For Efficient Cross-modal Retrieval (2016)11.67