# Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition

arXiv: https://arxiv.org/abs/2112.11679 · HTML: https://mlsanity.com/paper/2112.11679/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 22 Dec 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [A Holistic Visual Place Recognition Approach using Lightweight CNNs for Significant ViewPoint and Appearance Changes](https://mlsanity.com/paper/1811.03032/) (2018)
- [Recent Advance in Content-based Image Retrieval: A Literature Survey](https://mlsanity.com/paper/1706.06064/) (2017)
- [Bags of Local Convolutional Features for Scalable Instance Search](https://mlsanity.com/paper/1604.04653/) (2016)
- [CAMAL: Context-Aware Multi-layer Attention framework for Lightweight Environment Invariant Visual Place Recognition](https://mlsanity.com/paper/1909.08153/) (2019)

## Built on by (most cited first, 1 of 1)

- [SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models](https://mlsanity.com/paper/2506.13073/) (2025)

## Abstract (arXiv)

Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance. Thanks to the practical feature extraction ability of the lightweight convolution neural networks (CNNs) and the train-ability of the vector of locally aggregated descriptors (VLAD) layer, we propose a lightweight weakly supervised end-to-end neural network consisting of a front-ended perception model called GhostCNN and a learnable VLAD layer as a back-end. GhostCNN is based on Ghost modules that are lightweight CNN-based architectures. They can generate redundant feature maps using linear operations instead of the traditional convolution process, making a good trade-off between computation resources and recognition accuracy. To enhance our proposed lightweight model further, we add dilated convolutions to the Ghost module to get features containing more spatial semantic information, improving accuracy. Finally, rich experiments conducted on a commonly used public benchmark and our private dataset validate that the proposed neural network reduces the FLOPs and parameters of VGG16-NetVLAD by 99.04% and 80.16%, respectively. Besides, both models achieve similar accuracy.