Transformer Assisted U-Net for Marine Litter Detection on Sentinel-2 Imagery

The contamination of marine environments with man-made litter is a growing nation-wide concern. Satellite imagery combined with deep learning–based detection models has emerged as a robust and cost-effective solution for large-scale marine litter monitoring. In this article, we present a novel deep learning-based scheme to detect marine litter using Sentinel-2 imagery based on the Deep UNet architecture, introducing self- and cross-attention mechanisms into the decoder via transformer layers. The model leverages all Sentinel-2 bands except B10, and the NDVI and FDI indices are additionally incorporated to better guide the segmentation process. To evaluate the proposed model, we train it on the FloatingObjects dataset, a widely used benchmark for marine debris detection, and compare its performance against state-of-the-art approaches.