Hyperbolic Hierarchical Contrastive Hashing

Abstract

Hierarchical semantic structures, naturally existing in real-world datasets, can assist in capturing the latent distribution of data to learn robust hash codes for retrieval systems. Although hierarchical semantic structures can be simply expressed by integrating semantically relevant data into a high-level taxon with coarser-grained semantics, the construction, embedding, and exploitation of the structures remain tricky for unsupervised hash learning. To tackle these problems, we propose a novel unsupervised hashing method named Hyperbolic Hierarchical Contrastive Hashing (HHCH). We propose to embed continuous hash codes into hyperbolic space for accurate semantic expression since embedding hierarchies in hyperbolic space generates less distortion than in hyper-sphere space and Euclidean space. In addition, we extend the K-Means algorithm to hyperbolic space and perform the proposed hierarchical hyperbolic K-Means algorithm to construct hierarchical semantic structures adaptively. To

Stats

• citations28
• S2 citations—
• github stars0
• HF likes0
• heat score10.97
• arxiv keywei2022hyperbolic

Related papers

• Weighted Contrastive Hashing (2022)0.00
• Supervised Deep Hashing For Hierarchical Labeled Data (2017)8.09
• Learning Visual Hierarchies In Hyperbolic Space For Image Retrieval (2024)0.00
• Deep Collaborative Discrete Hashing With Semantic-invariant Structure (2019)8.09
• Unsupervised Hashing With Contrastive Information Bottleneck (2021)13.50
• Semantic Hierarchy Preserving Deep Hashing For Large-scale Image Retrieval (2019)5.24
• Exploring Auxiliary Context: Discrete Semantic Transfer Hashing For Scalable Image Retrieval (2019)15.88
• Hierarchy Neighborhood Discriminative Hashing For An Unified View Of Single-label And Multi-label Image Retrieval (2019)0.00