Hierarchical Attention Fusion For Geo-localization

Abstract

Geo-localization is a critical task in computer vision. In this work, we cast the geo-localization as a 2D image retrieval task. Current state-of-the-art methods for 2D geo-localization are not robust to locate a scene with drastic scale variations because they only exploit features from one semantic level for image representations. To address this limitation, we introduce a hierarchical attention fusion network using multi-scale features for geo-localization. We extract the hierarchical feature maps from a convolutional neural network (CNN) and organically fuse the extracted features for image representations. Our training is self-supervised using adaptive weights to control the attention of feature emphasis from each hierarchical level. Evaluation results on the image retrieval and the large-scale geo-localization benchmarks indicate that our method outperforms the existing state-of-the-art methods. Code is available here: https://github.com/YanLiqi/HAF.

Stats

• citations37
• S2 citations—
• github stars12
• HF likes0
• heat score14.08
• arxiv keyyan2021hierarchical

Code

• YanLiqi/HAF—

Related papers

• A Unified Hierarchical Framework For Fine-grained Cross-view Geo-localization Over Large-scale Scenarios (2025)0.00
• Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16
• Supergf: Unifying Local And Global Features For Visual Localization (2022)0.00
• All The Attention You Need: Global-local, Spatial-channel Attention For Image Retrieval (2021)13.97
• Scaling Image Geo-localization To Continent Level (2025)0.00
• Localizing And Orienting Street Views Using Overhead Imagery (2016)17.26
• Hierloc: Hyperbolic Entity Embeddings For Hierarchical Visual Geolocation (2026)0.00
• Densernet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation (2020)15.62