An Interpretable Deep Semantic Segmentation Method for Earth Observation.

Zhang, Ziyang and Angelov, Plamen and Soares, Eduardo and Longépé, Nicolas and Mathieu, Pierre-Philippe (2022) An Interpretable Deep Semantic Segmentation Method for Earth Observation. arXiv, abs/22. ISSN 2331-8422

Full text not available from this repository.

Abstract

Earth observation is fundamental for a range of human activities including flood response as it offers vital information to decision makers. Semantic segmentation plays a key role in mapping the raw hyper-spectral data coming from the satellites into a human understandable form assigning class labels to each pixel. In this paper, we introduce a prototype-based interpretable deep semantic segmentation (IDSS) method, which is highly accurate as well as interpretable. Its parameters are in orders of magnitude less than the number of parameters used by deep networks such as U-Net and are clearly interpretable by humans. The proposed here IDSS offers a transparent structure that allows users to inspect and audit the algorithm's decision. Results have demonstrated that IDSS could surpass other algorithms, including U-Net, in terms of IoU (Intersection over Union) total water and Recall total water. We used WorldFloods data set for our experiments and plan to use the semantic segmentation results combined with masks for permanent water to detect flood events.

Item Type:
Journal Article
Journal or Publication Title:
arXiv
ID Code:
180717
Deposited By:
Deposited On:
09 Dec 2022 15:05
Refereed?:
Yes
Published?:
Published
Last Modified:
25 Jan 2023 02:07