# Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization

arXiv: https://arxiv.org/abs/2412.14819 · HTML: https://mlsanity.com/paper/2412.14819/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching](https://mlsanity.com/paper/2005.03860/) (2020)
- [Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization](https://mlsanity.com/paper/2103.06818/) (2021)
- [Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation](https://mlsanity.com/paper/2303.11851/) (2023)
- [Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization](https://mlsanity.com/paper/2008.11646/) (2020)
- [Optimal Feature Transport for Cross-View Image Geo-Localization](https://mlsanity.com/paper/1907.05021/) (2019)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence](https://mlsanity.com/paper/2212.04074/) (2022)
- [SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite](https://mlsanity.com/paper/2204.10704/) (2022)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching](https://mlsanity.com/paper/2203.14148/) (2022)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs](https://mlsanity.com/paper/2303.14672/) (2023)
- [GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglement](https://mlsanity.com/paper/2308.09624/) (2023)
- [Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark](https://mlsanity.com/paper/2205.15761/) (2022)
- [SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization](https://mlsanity.com/paper/2403.04172/) (2024)
- [Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials](https://mlsanity.com/paper/2307.03398/) (2023)

## Built on by (most cited first, 16 of 16)

- [Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization](https://mlsanity.com/paper/2502.11381/) (2025)
- [SkyLink: Unifying Street-Satellite Geo-Localization via UAV-Mediated 3D Scene Alignment](https://mlsanity.com/paper/2509.24783/) (2025)
- [DiffusionUavLoc: Visually Prompted Diffusion for Cross-View UAV Localization](https://mlsanity.com/paper/2511.06422/) (2025)
- [Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization](https://mlsanity.com/paper/2512.19365/) (2025)
- [Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation](https://mlsanity.com/paper/2512.23938/) (2025)
- [MOGeo: Beyond One-to-One Cross-View Object Geo-localization](https://mlsanity.com/paper/2603.13843/) (2026)
- [From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization](https://mlsanity.com/paper/2503.07520/) (2025)
- [GLEAM: Learning to Match and Explain in Cross-View Geo-Localization](https://mlsanity.com/paper/2509.07450/) (2025)
- [Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery](https://mlsanity.com/paper/2605.11654/) (2026)
- [Dynamic Contrastive Learning for Hierarchical Retrieval: A Case Study of Distance-Aware Cross-View Geo-Localization](https://mlsanity.com/paper/2506.23077/) (2025)
- [(MGS)2-Net: Unifying Micro-Geometric Scale and Macro-Geometric Structure for Cross-View Geo-Localization](https://mlsanity.com/paper/2602.10704/) (2026)
- [Cross-view geo-localization, Image retrieval, Multiscale geometric modeling, Frequency domain enhancement](https://mlsanity.com/paper/2603.02726/) (2026)
- [BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization](https://mlsanity.com/paper/2605.10345/) (2026)
- [Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse](https://mlsanity.com/paper/2605.14925/) (2026)
- [DINO-GFSA: Geo-Localization via Semantic Gated Fusion and Mamba-based Sequential Aggregation](https://mlsanity.com/paper/2606.00784/) (2026)
- [A Unified Benchmark and Modality-Adaptive Network for Day-and-Night Drone-View Geo-Localization](https://mlsanity.com/paper/2607.25778/) (2026)

## Abstract (arXiv)

Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in viewpoints are substantial, which limits the ability of existing methods to effectively associate cross-view features and extract consistent and invariant characteristics. Moreover, existing methods often overlook the problem of increased computational and storage requirements when improving model performance. To handle these limitations, we propose a lightweight enhanced alignment network, called the Multi-Level Embedding and Alignment Network (MEAN). The MEAN network uses a progressive multi-level enhancement strategy, global-to-local associations, and cross-domain alignment, enabling feature communication across levels. This allows MEAN to effectively connect features at different levels and learn robust cross-view consistent mappings and modality-invariant features. Moreover, MEAN adopts a shallow backbone network combined with a lightweight branch design, effectively reducing parameter count and computational complexity. Experimental results on the University-1652 and SUES-200 datasets demonstrate that MEAN reduces parameter count by 62.17% and computational complexity by 70.99% compared to state-of-the-art models, while maintaining competitive or even superior performance. Our code and models will be released on https://github.com/ISChenawei/MEAN.