Revisiting Aerial Scene Classification on the AID Benchmark

TL;DR

This paper reviews machine learning methods for aerial scene classification, introduces a new attention-enhanced CNN model called Aerial-Y-Net, and demonstrates its superior performance on the AID dataset.

Contribution

The paper presents Aerial-Y-Net, a novel spatial attention CNN with multi-scale feature fusion, improving aerial scene classification accuracy.

Findings

Aerial-Y-Net achieves 91.72% accuracy on AID dataset.

The model outperforms baseline architectures.

Attention mechanisms enhance understanding of aerial images.

Abstract

Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature, developing robust models for scene classification remains a challenge. In this study, we conduct a literature review of various machine learning methods for aerial image classification. Our survey covers a range of approaches from handcrafted features (e.g., SIFT, LBP) to traditional CNNs (e.g., VGG, GoogLeNet), and advanced deep hybrid networks. In this connection, we have also designed Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion mechanism, which acts as an attention-based model and helps us to better understand the complexities of aerial images. Evaluated on the AID dataset, our model achieves 91.72% accuracy, outperforming several baseline architectures.