An Interpretable Deep Semantic Segmentation Method for Earth Observation

TL;DR

This paper introduces an interpretable deep semantic segmentation method for earth observation data that is highly accurate, transparent, and easier to interpret than traditional deep networks, with promising results on flood detection.

Contribution

The paper presents a prototype-based interpretable deep semantic segmentation method that reduces complexity and enhances interpretability compared to existing models like U-Net.

Findings

IDSS surpasses U-Net in IoU and Recall for total water.

IDSS has significantly fewer parameters than traditional deep networks.

Experimental validation on WorldFloods dataset demonstrates effectiveness.

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.