# Patch-DrosoNet: Classifying Image Partitions With Fly-Inspired Models For Lightweight Visual Place Recognition

arXiv: https://arxiv.org/abs/2305.05256 · HTML: https://mlsanity.com/paper/2305.05256/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 9 May 2023.

## Builds on (most cited first, 10 of 10)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [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)
- [Lightweight Unsupervised Deep Loop Closure](https://mlsanity.com/paper/1805.07703/) (2018)
- [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)

## Abstract (arXiv)

Visual place recognition (VPR) enables autonomous systems to localize themselves within an environment using image information. While Convolution Neural Networks (CNNs) currently dominate state-of-the-art VPR performance, their high computational requirements make them unsuitable for platforms with budget or size constraints. This has spurred the development of lightweight algorithms, such as DrosoNet, which employs a voting system based on multiple bio-inspired units. In this paper, we present a novel training approach for DrosoNet, wherein separate models are trained on distinct regions of a reference image, allowing them to specialize in the visual features of that specific section. Additionally, we introduce a convolutional-like prediction method, in which each DrosoNet unit generates a set of place predictions for each portion of the query image. These predictions are then combined using the previously introduced voting system. Our approach significantly improves upon the VPR performance of previous work while maintaining an extremely compact and lightweight algorithm, making it suitable for resource-constrained platforms.