Multi-class segmentation under severe class imbalance: A case study in roof damage assessment
arXiv:2010.07151
Abstract
The task of roof damage classification and segmentation from overhead imagery presents unique challenges. In this work we choose to address the challenge posed due to strong class imbalance. We propose four distinct techniques that aim at mitigating this problem. Through a new scheme that feeds the data to the network by oversampling the minority classes, and three other network architectural improvements, we manage to boost the macro-averaged F1-score of a model by 39.9 percentage points, thus achieving improved segmentation performance, especially on the minority classes.
Submitted to the Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop at NeurIPS 2020
References in corpus (7)
- Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
- Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks
- From Satellite Imagery to Disaster Insights
- FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
- Inundation Modeling in Data Scarce Regions
- Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector
- Explainable Semantic Mapping for First Responders