Lune

ICCV2023Top-tier venue

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

Gabriele Trivigno, Gabriele Moreno Berton, Juan Aragon, Barbara Caputo, Carlo Masone

Abstract

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. Code is available at https://github.com/ga1i13o/Divide-and-Classify

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Rethinking Visual Geo-localization for Large-Scale Applications cites Scalable Place Recognition Under Appearance Change for Autonomous Driving
  • Rethinking Visual Geo-localization for Large-Scale Applications cites Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Understanding Contrastive Representation Learning through Alignment and Uniformity on the HypersphereTongzhou Wang, Phillip IsolaICML 2020 · 2,360 citations
  2. Rethinking Visual Geo-localization for Large-Scale ApplicationsGabriele Moreno Berton, Carlo Masone, Barbara CaputoCVPR 2022 · 235 citations
  3. TransVPR: Transformer-Based Place Recognition with Multi-Level Attention AggregationRuotong Wang, Yanqing Shen, Weiliang Zuo, Sanping Zhou et al.CVPR 2022 · 167 citations
  4. Stochastic Attraction-Repulsion Embedding for Large Scale Image LocalizationLiu Liu, Hongdong Li, Yuchao DaiICCV 2019 · 123 citations
  5. Scalable Place Recognition Under Appearance Change for Autonomous DrivingDzung A. Doan, Yasir Latif, Tat-Jun Chin, Yu Liu et al.ICCV 2019 · 81 citations

Related papers

  1. EigenPlaces: Training Viewpoint Robust Models for Visual Place RecognitionGabriele Moreno Berton, Gabriele Trivigno, Barbara Caputo, Carlo MasoneICCV 2023 · 141 citations
  2. MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive ClusteringQiwen Gu, Xufei Wang, Junqiao Zhao, Siyue Tao et al.NeurIPS 2025 · 6 citations
  3. Data-Efficient Large Scale Place Recognition with Graded Similarity SupervisionMaria Leyva-Vallina, Nicola Strisciuglio, Nicolai PetkovCVPR 2023
  4. Efficient Large-scale Localization by Global Instance RecognitionFei Xue, Ignas Budvytis, Daniel Olmeda Reino, Roberto CipollaCVPR 2022 · 19 citations
  5. SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place RecognitionShunpeng Chen, Changwei Wang, Rongtao Xu, Xingtian Pei et al.ICLR 2026 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines