Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing
International Journal of Applied Earth Observation and Geoinformation(2021)
摘要
•We evaluated quantitatively and qualitatively different aspects of ten XAI methods.•We employed various metrics in order to assess XAI methods’ performance.•XAI methods for multi-label classification tasks in BigEarthNet and SEN12MS datasets.•Extracted significant insights regarding models’ decisions and datasets’ composition.•Occlusion, LIME and Grad-CAM were the most interpretable methods.
更多查看译文
关键词
Interpretability,Explainability,Deep neural networks,XAI,Black-box models,BigEarthNet,SEN12MS
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要