# Beyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition

arXiv: https://arxiv.org/abs/2103.08366 · HTML: https://mlsanity.com/paper/2103.08366/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 15 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [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)
- [Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)](https://mlsanity.com/paper/1610.02455/) (2016)
- [Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset](https://mlsanity.com/paper/2002.10152/) (2020)
- [Unsupervised Learning Methods for Visual Place Recognition in Discretely and Continuously Changing Environments](https://mlsanity.com/paper/2001.08960/) (2020)
- [Graph-based non-linear least squares optimization for visual place recognition in changing environments](https://mlsanity.com/paper/2012.14766/) (2020)
- [MILD: Multi-Index hashing for Loop closure Detection](https://mlsanity.com/paper/1702.08780/) (2017)

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

- [Visual Place Recognition: A Tutorial](https://mlsanity.com/paper/2303.03281/) (2023)
- [What makes visual place recognition easy or hard?](https://mlsanity.com/paper/2106.12671/) (2021)
- [Patch-NetVLAD+: Learned patch descriptor and weighted matching strategy for place recognition](https://mlsanity.com/paper/2202.05738/) (2022)
- [Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition](https://mlsanity.com/paper/2602.04401/) (2026)
- [Adaptive Thresholding for Visual Place Recognition using Negative Gaussian Mixture Statistics](https://mlsanity.com/paper/2512.09071/) (2025)
- [Breaking D'ej`a Vu: Independent Auditing of Visual Place Recognition through Vision-Language Reasoning](https://mlsanity.com/paper/2607.12818/) (2026)

## Abstract (arXiv)

Visual place recognition is the task of recognizing same places of query images in a set of database images, despite potential condition changes due to time of day, weather or seasons. It is important for loop closure detection in SLAM and candidate selection for global localization. Many approaches in the literature perform computationally inefficient full image comparisons between queries and all database images. There is still a lack of suited methods for efficient place recognition that allow a fast, sparse comparison of only the most promising image pairs without any loss in performance. While this is partially given by ANN-based methods, they trade speed for precision and additional memory consumption, and many cannot find arbitrary numbers of matching database images in case of loops in the database. In this paper, we propose a novel fast sequence-based method for efficient place recognition that can be applied online. It uses relocalization to recover from sequence losses, and exploits usually available but often unused intra-database similarities for a potential detection of all matching database images for each query in case of loops or stops in the database. We performed extensive experimental evaluations over five datasets and 21 sequence combinations, and show that our method outperforms two state-of-the-art approaches and even full image comparisons in many cases, while providing a good tradeoff between performance and percentage of evaluated image pairs. Source code for Matlab will be provided with publication of this paper.