# Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition

arXiv: https://arxiv.org/abs/2103.01486 · HTML: https://mlsanity.com/paper/2103.01486/

## Key facts

- Cited by 238 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 92 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 30 of 48)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [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)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Deep Learning Features at Scale for Visual Place Recognition](https://mlsanity.com/paper/1701.05105/) (2017)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [DGC-Net: Dense Geometric Correspondence Network](https://mlsanity.com/paper/1810.08393/) (2018)
- [Aggregating Deep Convolutional Features for Image Retrieval](https://mlsanity.com/paper/1510.07493/) (2015)
- [Learnable pooling with Context Gating for video classification](https://mlsanity.com/paper/1706.06905/) (2017)
- [Night-to-Day Image Translation for Retrieval-based Localization](https://mlsanity.com/paper/1809.09767/) (2018)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Semantic Visual Localization](https://mlsanity.com/paper/1712.05773/) (2017)
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes](https://mlsanity.com/paper/1811.03032/) (2018)
- [Scalable Place Recognition Under Appearance Change for Autonomous Driving](https://mlsanity.com/paper/1908.00178/) (2019)
- [Detect-to-Retrieve: Efficient Regional Aggregation for Image Search](https://mlsanity.com/paper/1812.01584/) (2018)
- [Multi-scale Orderless Pooling of Deep Convolutional Activation Features](https://mlsanity.com/paper/1403.1840/) (2014)
- [Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods](https://mlsanity.com/paper/1903.03305/) (2019)
- [Event-based visual place recognition with ensembles of temporal windows](https://mlsanity.com/paper/2006.02826/) (2020)

## Built on by (most cited first, 30 of 238)

- [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)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [R2Former: Unified Retrieval and Reranking Transformer for Place Recognition](https://mlsanity.com/paper/2304.03410/) (2023)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (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)
- [ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance](https://mlsanity.com/paper/2303.16894/) (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)
- [Where in the World is this Image? Transformer-based Geo-localization in the Wild](https://mlsanity.com/paper/2204.13861/) (2022)
- [Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition](https://mlsanity.com/paper/2402.14505/) (2024)
- [Data-efficient Large Scale Place Recognition with Graded Similarity Supervision](https://mlsanity.com/paper/2303.11739/) (2023)
- [Text2Pos: Text-to-Point-Cloud Cross-Modal Localization](https://mlsanity.com/paper/2203.15125/) (2022)
- [OpenStreetView-5M: The Many Roads to Global Visual Geolocation](https://mlsanity.com/paper/2404.18873/) (2024)
- [SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition](https://mlsanity.com/paper/2105.00149/) (2021)
- [AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition](https://mlsanity.com/paper/2111.11739/) (2021)
- [Learning Super-Features for Image Retrieval](https://mlsanity.com/paper/2201.13182/) (2022)
- [The NeRFect Match: Exploring NeRF Features for Visual Localization](https://mlsanity.com/paper/2403.09577/) (2024)
- [Visual Place Recognition: A Tutorial](https://mlsanity.com/paper/2303.03281/) (2023)
- [SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs](https://mlsanity.com/paper/2404.00469/) (2024)
- [Generalized Contrastive Optimization of Siamese Networks for Place Recognition](https://mlsanity.com/paper/2103.06638/) (2021)
- [Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark](https://mlsanity.com/paper/2205.15761/) (2022)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization](https://mlsanity.com/paper/2210.04432/) (2022)

## Abstract (arXiv)

Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world. This paper introduces Patch-NetVLAD, which provides a novel formulation for combining the advantages of both local and global descriptor methods by deriving patch-level features from NetVLAD residuals. Unlike the fixed spatial neighborhood regime of existing local keypoint features, our method enables aggregation and matching of deep-learned local features defined over the feature-space grid. We further introduce a multi-scale fusion of patch features that have complementary scales (i.e. patch sizes) via an integral feature space and show that the fused features are highly invariant to both condition (season, structure, and illumination) and viewpoint (translation and rotation) changes. Patch-NetVLAD outperforms both global and local feature descriptor-based methods with comparable compute, achieving state-of-the-art visual place recognition results on a range of challenging real-world datasets, including winning the Facebook Mapillary Visual Place Recognition Challenge at ECCV2020. It is also adaptable to user requirements, with a speed-optimised version operating over an order of magnitude faster than the state-of-the-art. By combining superior performance with improved computational efficiency in a configurable framework, Patch-NetVLAD is well suited to enhance both stand-alone place recognition capabilities and the overall performance of SLAM systems.