A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification

by   Md. Adnan Arefeen, et al.

In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activation layers present in those blocks. The feature vector is then compressed into a low-dimensional feature space using dimension reduction algorithms on which we train a low-cost SVM classifier for the classification of the aerial images. We validate our choice of selected features based on the significance of the extracted features with respect to our classification pipeline. RBFF remarkably does not involve any training of the base CNN model except for a few parameters for the classifier, which makes the technique very cost-effective for practical deployments. The constructed model despite being lightweight outperforms several recently proposed models in terms of accuracy for a number of aerial scene datasets.


page 1

page 2

page 3

page 4


Laguerre-Gauss Preprocessing: Line Profiles as Image Features for Aerial Images Classification

An image preprocessing methodology based on Fourier analysis together wi...

Learning CNN filters from user-drawn image markers for coconut-tree image classification

Identifying species of trees in aerial images is essential for land-use ...

Cervical Cytology Classification Using PCA GWO Enhanced Deep Features Selection

Cervical cancer is one of the most deadly and common diseases among wome...

A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification

Existing deep learning based methods effectively prompt the performance ...

PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

This paper presents how we can achieve the state-of-the-art accuracy in ...

An Aerial Image Recognition Framework using Discrimination and Redundancy Quality Measure

Aerial image categorization plays an indispensable role in remote sensin...

Disaster Feature Classification on Aerial Photography to Explain Typhoon Damaged Region using Grad-CAM

Recent years, typhoon damages has become social problem owing to climate...