Evaluating Explainable Artificial Intelligence Methods for Multi-label Deep Learning Classification Tasks in Remote Sensing

04/03/2021
by   Ioannis Kakogeorgiou, et al.
274

Although deep neural networks hold the state-of-the-art in several remote sensing tasks, their black-box operation hinders the understanding of their decisions, concealing any bias and other shortcomings in datasets and model performance. To this end, we have applied explainable artificial intelligence (XAI) methods in remote sensing multi-label classification tasks towards producing human-interpretable explanations and improve transparency. In particular, we developed deep learning models with state-of-the-art performance in the benchmark BigEarthNet and SEN12MS datasets. Ten XAI methods were employed towards understanding and interpreting models' predictions, along with quantitative metrics to assess and compare their performance. Numerous experiments were performed to assess the overall performance of XAI methods for straightforward prediction cases, competing multiple labels, as well as misclassification cases. According to our findings, Occlusion, Grad-CAM and Lime were the most interpretable and reliable XAI methods. However, none delivers high-resolution outputs, while apart from Grad-CAM, both Lime and Occlusion are computationally expensive. We also highlight different aspects of XAI performance and elaborate with insights on black-box decisions in order to improve transparency, understand their behavior and reveal, as well, datasets' particularities.

READ FULL TEXT

page 27

page 28

page 29

page 33

page 38

page 39

page 41

page 42

research
10/01/2020

MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding

To better understand scene images in the field of remote sensing, multi-...
research
08/28/2017

Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models

With the availability of large databases and recent improvements in deep...
research
10/02/2018

An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images

Deep neural networks have established as a powerful tool for large scale...
research
01/17/2023

Training Methods of Multi-label Prediction Classifiers for Hyperspectral Remote Sensing Images

With their combined spectral depth and geometric resolution, hyperspectr...
research
01/26/2021

Introducing and assessing the explainable AI (XAI)method: SIDU

Explainable Artificial Intelligence (XAI) has in recent years become a w...
research
07/14/2022

Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification

We present 'AiTLAS: Benchmark Arena' – an open-source benchmark framewor...
research
03/30/2022

How Deep is Your Art: An Experimental Study on the Limits of Artistic Understanding in a Single-Task, Single-Modality Neural Network

Mathematical modeling and aesthetic rule extraction of works of art are ...

Please sign up or login with your details

Forgot password? Click here to reset