# Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique

arXiv: https://arxiv.org/abs/2210.07509 · HTML: https://mlsanity.com/paper/2210.07509/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 18 of 18)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (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)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes](https://mlsanity.com/paper/1811.03032/) (2018)
- [Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methods](https://mlsanity.com/paper/1903.03305/) (2019)
- [Lightweight Unsupervised Deep Loop Closure](https://mlsanity.com/paper/1805.07703/) (2018)
- [Hierarchical Multi-Process Fusion for Visual Place Recognition](https://mlsanity.com/paper/2002.03895/) (2020)
- [Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion](https://mlsanity.com/paper/2010.09228/) (2020)
- [Improving Visual Place Recognition Performance by Maximising Complementarity](https://mlsanity.com/paper/2102.08416/) (2021)
- [Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments](https://mlsanity.com/paper/2109.06452/) (2021)
- [Unsupervised Learning Methods for Visual Place Recognition in Discretely and Continuously Changing Environments](https://mlsanity.com/paper/2001.08960/) (2020)
- [What makes visual place recognition easy or hard?](https://mlsanity.com/paper/2106.12671/) (2021)
- [Filter Early, Match Late: Improving Network-Based Visual Place Recognition](https://mlsanity.com/paper/1906.12176/) (2019)

## Built on by (most cited first, 3 of 3)

- [Applications of Spiking Neural Networks in Visual Place Recognition](https://mlsanity.com/paper/2311.13186/) (2023)
- [Improving Visual Place Recognition Based Robot Navigation By Verifying Localization Estimates](https://mlsanity.com/paper/2407.08162/) (2024)
- [Dynamically Modulating Visual Place Recognition Sequence Length For Minimum Acceptable Performance Scenarios](https://mlsanity.com/paper/2407.00863/) (2024)

## Abstract (arXiv)

One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion. These approaches come with a substantial practical limitation: they require all potential VPR methods to be brute-force run before they are selectively fused. The obvious solution to this limitation is to predict the viable subset of methods ahead of time, but this is challenging because it requires a predictive signal within the imagery itself that is indicative of high performance methods. Here we propose an alternative approach that instead starts with a known single base VPR technique, and learns to predict the most complementary additional VPR technique to fuse with it, that results in the largest improvement in performance. The key innovation here is to use a dimensionally reduced difference vector between the query image and the top-retrieved reference image using this baseline technique as the predictive signal of the most complementary additional technique, both during training and inference. We demonstrate that our approach can train a single network to select performant, complementary technique pairs across datasets which span multiple modes of transportation (train, car, walking) as well as to generalise to unseen datasets, outperforming multiple baseline strategies for manually selecting the best technique pairs based on the same training data.