English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

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

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