A Deep-Learning Framework for Land-Sliding Classification from Remote Sensing Image
This work addresses the problem of automatic landslide classification for disaster management and remote sensing applications, but it is incremental as it combines existing methods like EfficientNet and SVM.
The paper tackled the challenge of selecting an appropriate deep learning architecture for landslide detection from remote sensing images to optimize performance and avoid overfitting, achieving an F1-score of 0.8938 on a public test set.
The use of satellite imagery combined with deep learning to support automatic landslide detection is becoming increasingly widespread. However, selecting an appropriate deep learning architecture to optimize performance while avoiding overfitting remains a critical challenge. To address these issues, we propose a deep-learning based framework for landslide detection from remote sensing image in this paper. The proposed framework presents an effective combination of the online an offline data augmentation to tackle the imbalanced data, a backbone EfficientNet\_Large deep learning model for extracting robust embedding features, and a post-processing SVM classifier to balance and enhance the classification performance. The proposed model achieved an F1-score of 0.8938 on the public test set of the Zindi challenge.