# CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement

arXiv: https://arxiv.org/abs/2311.11604 · HTML: https://mlsanity.com/paper/2311.11604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [High Quality Monocular Depth Estimation via Transfer Learning](https://mlsanity.com/paper/1812.11941/) (2018)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Learning and aggregating deep local descriptors for instance-level recognition](https://mlsanity.com/paper/2007.13172/) (2020)
- [Event-based visual place recognition with ensembles of temporal windows](https://mlsanity.com/paper/2006.02826/) (2020)
- [Augmenting Visual Place Recognition with Structural Cues](https://mlsanity.com/paper/2003.00278/) (2020)
- [Delta Descriptors: Change-Based Place Representation for Robust Visual Localization](https://mlsanity.com/paper/2006.05700/) (2020)
- [ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization](https://mlsanity.com/paper/2207.12317/) (2022)
- [GSLAM: A General SLAM Framework and Benchmark](https://mlsanity.com/paper/1902.07995/) (2019)

## Built on by (most cited first, 1 of 1)

- [DualGeo: A Dual-View Framework for Worldwide Image Geo-localization](https://mlsanity.com/paper/2604.25533/) (2026)

## Abstract (arXiv)

Visual geolocalization is a cost-effective and scalable task that involves matching one or more query images, taken at some unknown location, to a set of geo-tagged reference images. Existing methods, devoted to semantic features representation, evolving towards robustness to a wide variety between query and reference, including illumination and viewpoint changes, as well as scale and seasonal variations. However, practical visual geolocalization approaches need to be robust in appearance changing and extreme viewpoint variation conditions, while providing accurate global location estimates. Therefore, inspired by curriculum design, human learn general knowledge first and then delve into professional expertise. We first recognize semantic scene and then measure geometric structure. Our approach, termed CurriculumLoc, involves a delicate design of multi-stage refinement pipeline and a novel keypoint detection and description with global semantic awareness and local geometric verification. We rerank candidates and solve a particular cross-domain perspective-n-point (PnP) problem based on these keypoints and corresponding descriptors, position refinement occurs incrementally. The extensive experimental results on our collected dataset, TerraTrack and a benchmark dataset, ALTO, demonstrate that our approach results in the aforementioned desirable characteristics of a practical visual geolocalization solution. Additionally, we achieve new high recall@1 scores of 62.6% and 94.5% on ALTO, with two different distances metrics, respectively. Dataset, code and trained models are publicly available on https://github.com/npupilab/CurriculumLoc.