Hierloc: Hyperbolic Entity Embeddings For Hierarchical Visual Geolocation
2026 · Hari Krishna Gadi, Daniel Matos, Hongyi Luo, et al.
Abstract
Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geography. Existing paradigms rely on either large-scale retrieval, which requires storing a large number of image embeddings, grid-based classifiers that ignore geographic continuity, or generative models that diffuse over space but struggle with fine detail. We introduce an entity-centric formulation of geolocation that replaces image-to-image retrieval with a compact hierarchy of geographic entities embedded in Hyperbolic space. Images are aligned directly to country, region, subregion, and city entities through Geo-Weighted Hyperbolic contrastive learning by directly incorporating haversine distance into the contrastive objective. This hierarchical design enables interpretable predictions and efficient inference with 240k entity embeddings instead of over 5 million image embeddings on the OSV5M benchmark, on
Authors
(none)
Tags
Stats
Related papers
- Learning Visual Hierarchies In Hyperbolic Space For Image Retrieval (2024)0.00
- ARGENT: Adaptive Hierarchical Image-text Representations (2026)0.00
- Hyperbolic Image Embeddings (2019)17.91
- Leveraging Efficientnet And Contrastive Learning For Accurate Global-scale Location Estimation (2021)9.03
- Hierarchical Attention Fusion For Geo-localization (2021)14.08
- Hypevpr: Exploring Hyperbolic Space For Perspective To Equirectangular Visual Place Recognition (2025)0.00
- Hyperbolic Hierarchical Contrastive Hashing (2022)10.97
- Air-hloc: Adaptive Retrieved Images Selection For Efficient Visual Localisation (2024)0.00