# Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing

arXiv: https://arxiv.org/abs/2104.01375 · HTML: https://mlsanity.com/paper/2104.01375/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 65 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion](https://mlsanity.com/paper/1906.07789/) (2019)
- [Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications](https://mlsanity.com/paper/2003.07631/) (2020)
- [Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution](https://mlsanity.com/paper/2004.10484/) (2020)
- [Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping -- Challenges and Opportunities](https://mlsanity.com/paper/2002.08254/) (2020)
- [BigEarthNet Dataset with A New Class-Nomenclature for Remote Sensing Image Understanding](https://mlsanity.com/paper/2001.06372/) (2020)
- [Kernel Methods and their derivatives: Concept and perspectives for the Earth system sciences](https://mlsanity.com/paper/2007.14706/) (2020)
- [A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification](https://mlsanity.com/paper/2009.13935/) (2020)

## Built on by (most cited first, 26 of 26)

- [The Role of Explainability in Assuring Safety of Machine Learning in Healthcare](https://mlsanity.com/paper/2109.00520/) (2021)
- [AI Security for Geoscience and Remote Sensing: Challenges and Future Trends](https://mlsanity.com/paper/2212.09360/) (2022)
- [Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics](https://mlsanity.com/paper/2409.16756/) (2024)
- [Benchmarking and scaling of deep learning models for land cover image classification](https://mlsanity.com/paper/2111.09451/) (2021)
- [Extending Logic Explained Networks to Text Classification](https://mlsanity.com/paper/2211.09732/) (2022)
- [KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation](https://mlsanity.com/paper/2408.07040/) (2024)
- [Exploring Wilderness Characteristics Using Explainable Machine Learning in Satellite Imagery](https://mlsanity.com/paper/2203.00379/) (2022)
- [Local Interpretable Model Agnostic Shap Explanations for machine learning models](https://mlsanity.com/paper/2210.04533/) (2022)
- [ODExAI: A Comprehensive Object Detection Explainable AI Evaluation](https://mlsanity.com/paper/2504.19249/) (2025)
- [On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification](https://mlsanity.com/paper/2507.05916/) (2025)
- [A Comprehensive Review of Agricultural Parcel and Boundary Delineation from Remote Sensing Images: Recent Progress and Future Perspectives](https://mlsanity.com/paper/2508.14558/) (2025)
- [Example-Based Explainable AI and its Application for Remote Sensing Image Classification](https://mlsanity.com/paper/2302.01526/) (2023)
- [Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification](https://mlsanity.com/paper/2306.04037/) (2023)
- [Towards Bridging the FL Performance-Explainability Trade-Off: A Trustworthy 6G RAN Slicing Use-Case](https://mlsanity.com/paper/2307.12903/) (2023)
- [Faithful and Robust Local Interpretability for Textual Predictions](https://mlsanity.com/paper/2311.01605/) (2023)
- [Explainable AI for Earth Observation: Current Methods, Open Challenges, and Opportunities](https://mlsanity.com/paper/2311.04491/) (2023)
- [Explainable Earth Surface Forecasting under Extreme Events](https://mlsanity.com/paper/2410.01770/) (2024)
- [Explainable Analysis of Deep Learning Methods for SAR Image Classification](https://mlsanity.com/paper/2204.06783/) (2022)
- [TEFL: Turbo Explainable Federated Learning for 6G Trustworthy Zero-Touch Network Slicing](https://mlsanity.com/paper/2210.10147/) (2022)
- [Transforming gradient-based techniques into interpretable methods](https://mlsanity.com/paper/2401.14434/) (2024)
- [Applications of Explainable artificial intelligence in Earth system science](https://mlsanity.com/paper/2406.11882/) (2024)
- [Boosting the Generalization Ability for Hyperspectral Image Classification using Spectral-spatial Axial Aggregation Transformer](https://mlsanity.com/paper/2306.16759/) (2023)
- [Underwater SONAR Image Classification and Analysis using LIME-based Explainable Artificial Intelligence](https://mlsanity.com/paper/2408.12837/) (2024)
- [IMPACTX: improving model performance by appropriately constraining the training with teacher explanations](https://mlsanity.com/paper/2502.12222/) (2025)
- [Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping](https://mlsanity.com/paper/2604.26051/) (2026)
- [Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing](https://mlsanity.com/paper/2609.38603/) (2026)

## Abstract (arXiv)

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 utilized and trained 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.