# Transformer-Guided Convolutional Neural Network for Cross-View Geolocalization

arXiv: https://arxiv.org/abs/2204.09967 · HTML: https://mlsanity.com/paper/2204.09967/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching](https://mlsanity.com/paper/2005.03860/) (2020)
- [Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization](https://mlsanity.com/paper/2008.11646/) (2020)
- [Bridging the Domain Gap for Ground-to-Aerial Image Matching](https://mlsanity.com/paper/1904.11045/) (2019)
- [Localizing and Orienting Street Views Using Overhead Imagery](https://mlsanity.com/paper/1608.00161/) (2016)
- [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)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images](https://mlsanity.com/paper/1710.02726/) (2017)
- [GeoCapsNet: Aerial to Ground view Image Geo-localization using Capsule Network](https://mlsanity.com/paper/1904.06281/) (2019)
- [Towards seamless multi-view scene analysis from satellite to street-level](https://mlsanity.com/paper/1705.08101/) (2017)
- [Cross-view Geo-localization with Evolving Transformer](https://mlsanity.com/paper/2107.00842/) (2021)

## Built on by (most cited first, 6 of 6)

- [GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglement](https://mlsanity.com/paper/2308.09624/) (2023)
- [CV-Cities: Advancing Cross-View Geo-Localization in Global Cities](https://mlsanity.com/paper/2411.12431/) (2024)
- [Cross-view geo-localization: a survey](https://mlsanity.com/paper/2406.09722/) (2024)
- [Cross-View Visual Geo-Localization for Outdoor Augmented Reality](https://mlsanity.com/paper/2303.15676/) (2023)
- [A Deep Learning Framework with Geographic Information Adaptive Loss for Remote Sensing Images based UAV Self-Positioning](https://mlsanity.com/paper/2502.16164/) (2025)
- [Lifting Vision: Ground to Aerial Localization with Reasoning Guided Planning](https://mlsanity.com/paper/2512.24404/) (2025)

## Abstract (arXiv)

Ground-to-aerial geolocalization refers to localizing a ground-level query image by matching it to a reference database of geo-tagged aerial imagery. This is very challenging due to the huge perspective differences in visual appearances and geometric configurations between these two views. In this work, we propose a novel Transformer-guided convolutional neural network (TransGCNN) architecture, which couples CNN-based local features with Transformer-based global representations for enhanced representation learning. Specifically, our TransGCNN consists of a CNN backbone extracting feature map from an input image and a Transformer head modeling global context from the CNN map. In particular, our Transformer head acts as a spatial-aware importance generator to select salient CNN features as the final feature representation. Such a coupling procedure allows us to leverage a lightweight Transformer network to greatly enhance the discriminative capability of the embedded features. Furthermore, we design a dual-branch Transformer head network to combine image features from multi-scale windows in order to improve details of the global feature representation. Extensive experiments on popular benchmark datasets demonstrate that our model achieves top-1 accuracy of 94.12% and 84.92% on CVUSA and CVACTval, respectively, which outperforms the second-performing baseline with less than 50% parameters and almost 2x higher frame rate, therefore achieving a preferable accuracy-efficiency tradeoff.