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.
翻译:自然存在于现实世界数据集中的等级语义结构,自然地存在于现实世界数据集中,可以帮助捕捉数据的潜在分布,以学习强健的散列码。虽然等级等级语义结构可以通过将语义相关数据纳入高层次分类库来简单表达,高层次语义分类库,但结构的构建、嵌入和利用仍然难以在不受监督的散列学习中进行。为了解决这些问题,我们提议了一种新型的、不受监督的散列法,名为超双曲线高度对立的散列法(HHCH)。我们提议将连续的散列代码嵌入超双曲线空间,以便准确的语义表达。因为我们在超曲线空间嵌入等级语义类相关数据生成的扭曲性比高得多。此外,我们把K-Means算法推广到超曲线空间,并进行拟议的高等级超曲线K-Means算法算法,以适应性地构建等级结构结构。为了利用超双曲线空间的等级语义结构结构,我们设计了等级对比性比对等模型,我们设计了等级比对等模型进行对比性比对等模型的比较性比式数据分析。