ResAttUNet: Detecting Marine Debris using an Attention activated Residual UNet
This work addresses the problem of detecting marine debris for environmental monitoring, representing an incremental improvement over existing methods.
The paper tackles marine debris detection and segmentation from remote sensing images by introducing a novel attention-based segmentation technique, achieving state-of-the-art results that outperform the MARIDA benchmark.
Currently, a significant amount of research has been done in field of Remote Sensing with the use of deep learning techniques. The introduction of Marine Debris Archive (MARIDA), an open-source dataset with benchmark results, for marine debris detection opened new pathways to use deep learning techniques for the task of debris detection and segmentation. This paper introduces a novel attention based segmentation technique that outperforms the existing state-of-the-art results introduced with MARIDA. The paper presents a novel spatial aware encoder and decoder architecture to maintain the contextual information and structure of sparse ground truth patches present in the images. The attained results are expected to pave the path for further research involving deep learning using remote sensing images. The code is available at https://github.com/sheikhazhanmohammed/SADMA.git