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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Despite the breakthrough deep learning performances achieved for automaticobject detection, small target detection is still a challenging problem,especially when looking at fast and accurate solutions suitable for mobile oredge applications. In this work we present YOLO-S, a simple, fast and efficientnetwork for small target detection. The architecture exploits a small featureextractor based on Darknet20, as well as skip connection, via both bypass andconcatenation, and reshape-passthrough layer to alleviate the vanishinggradient problem, promote feature reuse across network and combine low-levelpositional information with more meaningful high-level information. To verifythe performances of YOLO-S, we build "AIRES", a novel dataset for cAr detectIonfRom hElicopter imageS acquired in Europe, and set up experiments on both AIRESand VEDAI datasets, benchmarking this architecture with four baselinedetectors. Furthermore, in order to handle efficiently the issue of datainsufficiency and domain gap when dealing with a transfer learning strategy, weintroduce a transitional learning task over a combined dataset based on DOTAv2and VEDAI and demonstrate that can enhance the overall accuracy with respect tomore general features transferred from COCO data. YOLO-S is from 25% to 50%faster than YOLOv3 and only 15-25% slower than Tiny-YOLOv3, outperforming alsoYOLOv3 in terms of accuracy in a wide range of experiments. Further simulationsperformed on SARD dataset demonstrate also its applicability to differentscenarios such as for search and rescue operations. Besides, YOLO-S has an 87%decrease of parameter size and almost one half FLOPs of YOLOv3, makingpractical the deployment for low-power industrial applications.

A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery