# HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval

arXiv: https://arxiv.org/abs/2401.07212 · HTML: https://mlsanity.com/paper/2401.07212/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2024.

## Built on by (most cited first, 11 of 11)

- [Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space](https://mlsanity.com/paper/2407.01290/) (2024)
- [Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval](https://mlsanity.com/paper/2411.17490/) (2024)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [PHyCLIP: ℓ1-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning](https://mlsanity.com/paper/2510.08919/) (2025)
- [NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval](https://mlsanity.com/paper/2404.11025/) (2024)
- [Hi-LSplat: Hierarchical 3D Language Gaussian Splatting](https://mlsanity.com/paper/2506.06822/) (2025)
- [A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations](https://mlsanity.com/paper/2603.14022/) (2026)
- [ARGENT: Adaptive Hierarchical Image-Text Representations](https://mlsanity.com/paper/2603.23311/) (2026)
- [Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI](https://mlsanity.com/paper/2609.17969/) (2026)
- [Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption](https://mlsanity.com/paper/2605.30089/) (2026)
- [Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution](https://mlsanity.com/paper/2609.29329/) (2026)

## Abstract (arXiv)

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 Hierarchical Hyperbolic Product Quantization (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.