Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between images are overlooked. Moreover, these methods predominantly focus on the Euclidean space for computational convenience, compromising their ability to map the multi-level semantic relationships between images effectively. To mitigate these shortcomings, we propose a novel unsupervised product quantization method dubbed \textbf{Hi}erarchical \textbf{H}yperbolic \textbf{P}roduct \textbf{Q}uantization (HiHPQ), which learns quantized representations by incorporating hierarchical semantic similarity within hyperbolic geometry. Specifically, we propose a hyperbolic product quantizer, where the hyperbolic codebook attention mechanism and the quantized contrastive learning on the hyperbolic product manifold are introduced to expedite quantization. Furthermore, we propose a hierarchical semantics learning module, designed to enhance the distinction between similar and non-matching images for a query by utilizing the extracted hierarchical semantics as an additional training supervision. Experiments on benchmarks show that our proposed method outperforms state-of-the-art baselines.

翻译：现有无监督深度乘积量化方法主要致力于增强同一图像不同视角间的相似度，却忽视了图像间蕴含的精细多层级语义相似性。此外，这类方法为计算便利性普遍基于欧几里得空间，导致其难以有效映射图像间的多层级语义关系。为克服上述缺陷，我们提出一种新型无监督乘积量化方法——层次化双曲乘积量化（HiHPQ），该方法通过将双曲几何中的层次化语义相似性融入量化表征学习过程。具体而言，我们提出双曲乘积量化器，其中引入双曲码本注意力机制与双曲乘积流形上的量化对比学习以加速量化过程。进一步，我们设计层次化语义学习模块，通过将提取的层次化语义作为额外训练监督信号，增强查询图像对相似图与非匹配图的判别能力。在多个基准数据集上的实验表明，本方法性能优于当前最优基线模型。