Central Similarity Quantization For Efficient Image And Video Retrieval

Abstract

Existing data-dependent hashing methods usually learn hash functions from pairwise or triplet data relationships, which only capture the data similarity locally, and often suffer from low learning efficiency and low collision rate. In this work, we propose a new *global* similarity metric, termed as *central similarity*, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy. We principally formulate the computation of the proposed central similarity metric by introducing a new concept, i.e., *hash center* that refers to a set of data points scattered in the Hamming space with a sufficient mutual distance between each other. We then provide an efficient method to construct well separated hash centers by leveraging the Hadamard matrix and Bernoulli distributions. Finally, we propose the Central Similarity Quantization (CSQ) that

Stats

• citations313
• S2 citations—
• github stars239
• HF likes0
• heat score23.49
• arxiv keyyuan2019central

Related papers

• Simultaneous Compression And Quantization: A Joint Approach For Efficient Unsupervised Hashing (2018)7.50
• Asymmetric Correlation Quantization Hashing For Cross-modal Retrieval (2020)10.74
• Interleaved Composite Quantization For High-dimensional Similarity Search (2019)0.00
• Instance-weighted Central Similarity For Multi-label Image Retrieval (2021)0.00
• Deep Supervised Hashing Leveraging Quadratic Spherical Mutual Information For Content-based Image Retrieval (2019)0.00
• Deep Hashing With Semantic Hash Centers For Image Retrieval (2025)2.26
• Improved Deep Classwise Hashing With Centers Similarity Learning For Image Retrieval (2021)5.84
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88