# Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization

arXiv: https://arxiv.org/abs/2502.11381 · HTML: https://mlsanity.com/paper/2502.11381/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 30 of 31)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [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)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [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)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [A Discriminatively Learned CNN Embedding for Person Re-identification](https://mlsanity.com/paper/1611.05666/) (2016)
- [Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence](https://mlsanity.com/paper/2212.04074/) (2022)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite](https://mlsanity.com/paper/2204.10704/) (2022)
- [Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments](https://mlsanity.com/paper/2201.09201/) (2022)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization](https://mlsanity.com/paper/2403.14198/) (2024)
- [SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization](https://mlsanity.com/paper/2403.04172/) (2024)
- [Learning Cross-view Visual Geo-localization without Ground Truth](https://mlsanity.com/paper/2403.12702/) (2024)
- [Feature Representation Learning for Unsupervised Cross-domain Image Retrieval](https://mlsanity.com/paper/2207.09721/) (2022)
- [Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID](https://mlsanity.com/paper/2305.12673/) (2023)
- [Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization](https://mlsanity.com/paper/2412.14819/) (2024)
- [Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID](https://mlsanity.com/paper/2003.06650/) (2020)
- [MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2008.04015/) (2020)

## Built on by (most cited first, 4 of 4)

- [Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization](https://mlsanity.com/paper/2512.19365/) (2025)
- [Cross-view geo-localization, Image retrieval, Multiscale geometric modeling, Frequency domain enhancement](https://mlsanity.com/paper/2603.02726/) (2026)
- [Satellite-Free Training for Drone-View Geo-Localization](https://mlsanity.com/paper/2604.01581/) (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)

Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images. However, most existing methods heavily rely on strictly pre-paired drone-satellite images for supervised learning. When the target region shifts, new paired samples are typically required to adapt to the distribution changes. The high cost of annotation and the limited transferability of these methods significantly hinder the practical deployment of DVGL in open-world scenarios. To address these limitations, we propose a novel end-to-end self-supervised learning method with a shallow backbone network, called the dynamic memory-driven and neighborhood information learning (DMNIL) method. It employs a clustering algorithm to generate pseudo-labels and adopts a dual-path contrastive learning framework to learn discriminative intra-view representations. Furthermore, DMNIL incorporates two core modules, including the dynamic hierarchical memory learning (DHML) module and the information consistency evolution learning (ICEL) module. The DHML module combines short-term and long-term memory to enhance intra-view feature consistency and discriminability. Meanwhile, the ICEL module utilizes a neighborhood-driven dynamic constraint mechanism to systematically capture implicit cross-view semantic correlations, consequently improving cross-view feature alignment. To further stabilize and strengthen the self-supervised training process, a pseudo-label enhancement strategy is introduced to enhance the quality of pseudo supervision. Extensive experiments on three public benchmark datasets demonstrate that the proposed method consistently outperforms existing self-supervised methods and even surpasses several state-of-the-art supervised methods. Our code is available at https://github.com/ISChenawei/DMNIL.