WATT-EffNet: A Lightweight and Accurate Model for Classifying Aerial Disaster Images

TL;DR

WATT-EffNet is a lightweight, attention-enhanced deep learning model designed for efficient aerial disaster image classification on UAVs, significantly improving accuracy and computational efficiency over existing models.

Contribution

The paper introduces WATT-EffNet, a novel lightweight architecture with width-wise modules and attention mechanisms, outperforming baseline EfficientNet in accuracy and efficiency for UAV-based disaster scene classification.

Findings

Up to 15 times higher accuracy than baseline

38.3% reduction in FLOPs for efficiency

Effective ablation study on width variations

Abstract

Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV's ability to promptly comprehend the crisis and optimally utilize its limited power and processing resources to narrow down search areas is crucial. Therefore, developing an efficient and lightweight method for scene classification is of utmost importance. However, current approaches tend to prioritize accuracy on benchmark datasets at the expense of computational efficiency. To address this shortcoming, we introduce the Wider ATTENTION EfficientNet (WATT-EffNet), a novel method that achieves higher accuracy with a more lightweight architecture compared to the baseline EfficientNet. The WATT-EffNet leverages width-wise incremental feature modules and attention mechanisms over width-wise features to ensure the network structure remains lightweight. We evaluate our method on a UAV-based aerial disaster image classification dataset and demonstrate that it outperforms the baseline by up to 15 times in terms of classification accuracy and 38.3% in terms of computing efficiency as measured by Floating Point Operations per second (FLOPs). Additionally, we conduct an ablation study to investigate the effect of varying the width of WATT-EffNet on accuracy and computational efficiency. Our code is available at \url{https://github.com/TanmDL/WATT-EffNet}.