Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Concept-based explanations of Segmentation and Detection models in Natural Disaster Management

Samar Heydari, Jawher Said, Galip Ümit Yolcu, Evgenii Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios Mygdalis, Ioannis Pitas, Sebastian Lapuschkin, Leila Arras

Abstract

Deep learning models for flood and wildfire segmentation and object detection enable precise, real-time disaster localization when deployed on embedded drone platforms. However, in natural disaster management, the lack of transparency in their decision-making process hinders human trust required for emergency response. To address this, we present an explainability framework for understanding flood segmentation and car detection predictions on the widely used PIDNet and YOLO architectures. More specifically, we introduce a novel redistribution strategy that extends Layer-wise Relevance Propagation (LRP) explanations for sigmoid-gated element-wise fusion layers. This extension allows LRP relevances to flow through the fusion modules of PIDNet, covering the entire computation graph back to the input image. Furthermore, we apply Prototypical Concept-based Explanations (PCX) to provide both local and global explanations at the concept level, revealing which learned features drive the segmentation and detection of specific disaster semantic classes. Experiments on a publicly available flood dataset show that our framework provides reliable and interpretable explanations while maintaining near real-time inference capabilities, rendering it suitable for deployment on resource-constrained platforms, such as Unmanned Aerial Vehicles (UAVs).

Concept-based explanations of Segmentation and Detection models in Natural Disaster Management

Abstract

Deep learning models for flood and wildfire segmentation and object detection enable precise, real-time disaster localization when deployed on embedded drone platforms. However, in natural disaster management, the lack of transparency in their decision-making process hinders human trust required for emergency response. To address this, we present an explainability framework for understanding flood segmentation and car detection predictions on the widely used PIDNet and YOLO architectures. More specifically, we introduce a novel redistribution strategy that extends Layer-wise Relevance Propagation (LRP) explanations for sigmoid-gated element-wise fusion layers. This extension allows LRP relevances to flow through the fusion modules of PIDNet, covering the entire computation graph back to the input image. Furthermore, we apply Prototypical Concept-based Explanations (PCX) to provide both local and global explanations at the concept level, revealing which learned features drive the segmentation and detection of specific disaster semantic classes. Experiments on a publicly available flood dataset show that our framework provides reliable and interpretable explanations while maintaining near real-time inference capabilities, rendering it suitable for deployment on resource-constrained platforms, such as Unmanned Aerial Vehicles (UAVs).
Paper Structure (17 sections, 2 equations, 4 figures)

This paper contains 17 sections, 2 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Deep learning for Natural Disaster Management
  4. Explainable AI
  5. Concept-based explanations
  6. Methods
  7. Layer-wise Relevance Propagation (LRP)
  8. Extending LRP to PIDNet
  9. Concept-based explanations for Segmentation and Detection
  10. Experimental results
  11. Setting: data and models
  12. PIDNet-small PIDNet
  13. YOLOv6s6 Li2024YOLOv6
  14. Evaluation of concept-based explanations
  15. Visualizing prototypes and concepts
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Perturbation-based evaluation of concept-based explanations. Top: PIDNet flood segmentation, Bottom: YOLOv6s6 car detection. Left: AOC for concept deletion, Right: AUC for concept insertion. The higher the AOC/AUC scores, the better. AOC/AUC scores averaged over all layers are given in parenthesis.
  • Figure 2: PCX prototypes, and their concept contributions, for car detection with YOLOv6s6.
  • Figure 3: PCX prototypes for flood segmentation with PIDNet.
  • Figure 4: PCX explanation of an outlier prediction for car detection with YOLOv6s6.