# R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

arXiv: https://arxiv.org/abs/2304.03410 · HTML: https://mlsanity.com/paper/2304.03410/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 64 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 30 of 35)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Learning to Navigate in Cities Without a Map](https://mlsanity.com/paper/1804.00168/) (2018)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)

## Built on by (most cited first, 30 of 102)

- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [An Outlook into the Future of Egocentric Vision](https://mlsanity.com/paper/2308.07123/) (2023)
- [BoQ: A Place is Worth a Bag of Learnable Queries](https://mlsanity.com/paper/2405.07364/) (2024)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition](https://mlsanity.com/paper/2402.14505/) (2024)
- [GLACE: Global Local Accelerated Coordinate Encoding](https://mlsanity.com/paper/2406.04340/) (2024)
- [G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models](https://mlsanity.com/paper/2405.14702/) (2024)
- [Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2403.19584/) (2024)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Are Local Features All You Need for Cross-Domain Visual Place Recognition?](https://mlsanity.com/paper/2304.05887/) (2023)
- [AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization](https://mlsanity.com/paper/2407.08156/) (2024)
- [Challenges and Trends in Egocentric Vision: A Survey](https://mlsanity.com/paper/2503.15275/) (2025)
- [GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization](https://mlsanity.com/paper/2505.13731/) (2025)
- [Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries](https://mlsanity.com/paper/2505.15420/) (2025)
- [Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval](https://mlsanity.com/paper/2405.18025/) (2024)
- [Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset](https://mlsanity.com/paper/2406.09383/) (2024)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval](https://mlsanity.com/paper/2408.03282/) (2024)
- [EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition](https://mlsanity.com/paper/2405.18065/) (2024)
- [Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers](https://mlsanity.com/paper/2410.06614/) (2024)
- [SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition](https://mlsanity.com/paper/2502.16601/) (2025)
- [EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography](https://mlsanity.com/paper/2405.05422/) (2024)
- [CityGuessr: City-Level Video Geo-Localization on a Global Scale](https://mlsanity.com/paper/2411.06344/) (2024)
- [EDTformer: An Efficient Decoder Transformer for Visual Place Recognition](https://mlsanity.com/paper/2412.00784/) (2024)
- [Scaling Image Geo-Localization to Continent Level](https://mlsanity.com/paper/2510.26795/) (2025)
- [MeshVPR: Citywide Visual Place Recognition Using 3D Meshes](https://mlsanity.com/paper/2406.02776/) (2024)
- [NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization](https://mlsanity.com/paper/2502.14638/) (2025)

## Abstract (arXiv)

Visual Place Recognition (VPR) estimates the location of query images by matching them with images in a reference database. Conventional methods generally adopt aggregated CNN features for global retrieval and RANSAC-based geometric verification for reranking. However, RANSAC only employs geometric information but ignores other possible information that could be useful for reranking, e.g. local feature correlations, and attention values. In this paper, we propose a unified place recognition framework that handles both retrieval and reranking with a novel transformer model, named R2Former. The proposed reranking module takes feature correlation, attention value, and xy coordinates into account, and learns to determine whether the image pair is from the same location. The whole pipeline is end-to-end trainable and the reranking module alone can also be adopted on other CNN or transformer backbones as a generic component. Remarkably, R2Former significantly outperforms state-of-the-art methods on major VPR datasets with much less inference time and memory consumption. It also achieves the state-of-the-art on the hold-out MSLS challenge set and could serve as a simple yet strong solution for real-world large-scale applications. Experiments also show vision transformer tokens are comparable and sometimes better than CNN local features on local matching. The code is released at https://github.com/Jeff-Zilence/R2Former.