# Aggregating Multiple Bio-Inspired Image Region Classifiers For Effective And Lightweight Visual Place Recognition

arXiv: https://arxiv.org/abs/2312.12995 · HTML: https://mlsanity.com/paper/2312.12995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 20 Dec 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [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)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [Lightweight Unsupervised Deep Loop Closure](https://mlsanity.com/paper/1805.07703/) (2018)
- [Visual Place Recognition: A Tutorial](https://mlsanity.com/paper/2303.03281/) (2023)
- [A Hybrid Compact Neural Architecture for Visual Place Recognition](https://mlsanity.com/paper/1910.06840/) (2019)
- [Levelling the Playing Field: A Comprehensive Comparison of Visual Place Recognition Approaches under Changing Conditions](https://mlsanity.com/paper/1903.09107/) (2019)
- [Convolutional Neural Network-Based Image Representation for Visual Loop Closure Detection](https://mlsanity.com/paper/1504.05241/) (2015)
- [An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2109.10986/) (2021)
- [Visual Place Recognition for Aerial Robotics: Exploring Accuracy-Computation Trade-off for Local Image Descriptors](https://mlsanity.com/paper/1908.00258/) (2019)
- [Are State-of-the-art Visual Place Recognition Techniques any Good for Aerial Robotics?](https://mlsanity.com/paper/1904.07967/) (2019)
- [Highly-Efficient Binary Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2202.12375/) (2022)
- [Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition](https://mlsanity.com/paper/2209.08723/) (2022)

## Abstract (arXiv)

Visual place recognition (VPR) enables autonomous systems to localize themselves within an environment using image information. While VPR techniques built upon a Convolutional Neural Network (CNN) backbone dominate state-of-the-art VPR performance, their high computational requirements make them unsuitable for platforms equipped with low-end hardware. Recently, a lightweight VPR system based on multiple bio-inspired classifiers, dubbed DrosoNets, has been proposed, achieving great computational efficiency at the cost of reduced absolute place retrieval performance. In this work, we propose a novel multi-DrosoNet localization system, dubbed RegionDrosoNet, with significantly improved VPR performance, while preserving a low-computational profile. Our approach relies on specializing distinct groups of DrosoNets on differently sliced partitions of the original image, increasing extrinsic model differentiation. Furthermore, we introduce a novel voting module to combine the outputs of all DrosoNets into the final place prediction which considers multiple top refence candidates from each DrosoNet. RegionDrosoNet outperforms other lightweight VPR techniques when dealing with both appearance changes and viewpoint variations. Moreover, it competes with computationally expensive methods on some benchmark datasets at a small fraction of their online inference time.