# Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition

arXiv: https://arxiv.org/abs/2307.08417 · HTML: https://mlsanity.com/paper/2307.08417/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 60 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [Deep Learning Features at Scale for Visual Place Recognition](https://mlsanity.com/paper/1701.05105/) (2017)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps](https://mlsanity.com/paper/1808.02130/) (2018)
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes](https://mlsanity.com/paper/1811.03032/) (2018)
- [Visual Instance Retrieval with Deep Convolutional Networks](https://mlsanity.com/paper/1412.6574/) (2014)
- [Data-efficient Large Scale Place Recognition with Graded Similarity Supervision](https://mlsanity.com/paper/2303.11739/) (2023)
- [Scalable Place Recognition Under Appearance Change for Autonomous Driving](https://mlsanity.com/paper/1908.00178/) (2019)
- [Benchmarking Image Retrieval for Visual Localization](https://mlsanity.com/paper/2011.11946/) (2020)
- [Adaptive-Attentive Geolocalization from few queries: a hybrid approach](https://mlsanity.com/paper/2010.06897/) (2020)
- [Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods](https://mlsanity.com/paper/1903.03305/) (2019)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation](https://mlsanity.com/paper/2105.07645/) (2021)
- [A Hybrid Compact Neural Architecture for Visual Place Recognition](https://mlsanity.com/paper/1910.06840/) (2019)
- [An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2109.10986/) (2021)

## Built on by (most cited first, 2 of 2)

- [Statewide Visual Geolocalization in the Wild](https://mlsanity.com/paper/2409.16763/) (2024)
- [To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition](https://mlsanity.com/paper/2504.06116/) (2025)

## Abstract (arXiv)

Visual Place recognition is commonly addressed as an image retrieval problem. However, retrieval methods are impractical to scale to large datasets, densely sampled from city-wide maps, since their dimension impact negatively on the inference time. Using approximate nearest neighbour search for retrieval helps to mitigate this issue, at the cost of a performance drop. In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search. We find that existing classification methods for coarse, planet-wide localization are not suitable for the fine-grained and city-wide setting. This is largely due to how the dataset is split into classes, because these methods are designed to handle a sparse distribution of photos and as such do not consider the visual aliasing problem across neighbouring classes that naturally arises in dense scenarios. Thus, we propose a partitioning scheme that enables a fast and accurate inference, preserving a simple learning procedure, and a novel inference pipeline based on an ensemble of novel classifiers that uses the prototypes learned via an angular margin loss. Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting. Moreover, we show that D&C can be paired with existing retrieval pipelines to speed up computations by over 20 times while increasing their recall, leading to new state-of-the-art results.