Hyperbolic Hierarchical Contrastive Hashing

by   Rukai Wei, et al.
Huazhong University of Science u0026 Technology

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 exploit the hierarchical semantic structures in hyperbolic space, we designed the hierarchical contrastive learning algorithm, including hierarchical instance-wise and hierarchical prototype-wise contrastive learning. Extensive experiments on four benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods. Codes will be released.


page 1

page 3

page 11

page 12


Hyperbolic Contrastive Learning

Learning good image representations that are beneficial to downstream ta...

CIMON: Towards High-quality Hash Codes

Recently, hashing is widely-used in approximate nearest neighbor search ...

Contrastive Multi-view Hyperbolic Hierarchical Clustering

Hierarchical clustering recursively partitions data at an increasingly f...

Weighted Contrastive Hashing

The development of unsupervised hashing is advanced by the recent popula...

Learning to Hash Naturally Sorts

Locality sensitive hashing pictures a list-wise sorting problem. Its tes...

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality

Given an image set without any labels, our goal is to train a model that...

Please sign up or login with your details

Forgot password? Click here to reset