Multiscale Feature Filtering Network for Image Recognition System in Unmanned Aerial Vehicle

Complexity 2021:1-11 (2021)

Abstract

For unmanned aerial vehicle, object detection at different scales is an important component for the visual recognition. Recent advances in convolutional neural networks have demonstrated that attention mechanism remarkably enhances multiscale representation of CNNs. However, most existing multiscale feature representation methods simply employ several attention blocks in the attention mechanism to adaptively recalibrate the feature response, which overlooks the context information at a multiscale level. To solve this problem, a multiscale feature filtering network is proposed in this paper for image recognition system in the UAV. A novel building block, namely, multiscale feature filtering module, is proposed for ResNet-like backbones and it allows feature-selective learning for multiscale context information across multiparallel branches. These branches employ multiple atrous convolutions at different scales, respectively, and further adaptively generate channel-wise feature responses by emphasizing channel-wise dependencies. Experimental results on CIFAR100 and Tiny ImageNet datasets reflect that the MFFNet achieves very competitive results in comparison with previous baseline models. Further ablation experiments verify that the MFFNet can achieve consistent performance gains in image classification and object detection tasks.

Download options

PhilArchive



    Upload a copy of this work     Papers currently archived: 72,856

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Analytics

Added to PP
2021-02-20

Downloads
1 (#1,560,988)

6 months
1 (#386,040)

Historical graph of downloads

Sorry, there are not enough data points to plot this chart.
How can I increase my downloads?

References found in this work

No references found.

Add more references

Citations of this work

No citations found.

Add more citations

Similar books and articles

Face Recognition Using Dct And Neural Micro-Classifier Network.Abdellatief Hussien AbouAli - 2018 - International Journal of Engineering and Information Systems (IJEAIS) 2 (3):27-35.