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

by   Qingyuan Gong, et al.

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


page 4

page 5


GhostNet: More Features from Cheap Operations

Deploying convolutional neural networks (CNNs) on embedded devices is di...

CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

The development of lightweight object detectors is essential due to the ...

Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition

Point cloud based retrieval for place recognition is still a challenging...

CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have ...

Feature Map Filtering: Improving Visual Place Recognition with Convolutional Calibration

Convolutional Neural Networks (CNNs) have recently been shown to excel a...

Super Interaction Neural Network

Recent studies have demonstrated that the convolutional networks heavily...

SdcNet: A Computation-Efficient CNN for Object Recognition

Extracting features from a huge amount of data for object recognition is...

Please sign up or login with your details

Forgot password? Click here to reset