Towards Explainable Land Cover Mapping: a Counterfactual-based Strategy
This work addresses the need for explainable AI in remote sensing for domain experts, though it is incremental as it builds on existing counterfactual methods.
The paper tackled the problem of making land cover classification from satellite image time series more interpretable by proposing a generative adversarial counterfactual approach that avoids prior assumptions on target classes and enforces time-contiguous perturbations, resulting in sparser and more plausible explanations.
Counterfactual explanations are an emerging tool to enhance interpretability of deep learning models. Given a sample, these methods seek to find and display to the user similar samples across the decision boundary. In this paper, we propose a generative adversarial counterfactual approach for satellite image time series in a multi-class setting for the land cover classification task. One of the distinctive features of the proposed approach is the lack of prior assumption on the targeted class for a given counterfactual explanation. This inherent flexibility allows for the discovery of interesting information on the relationship between land cover classes. The other feature consists of encouraging the counterfactual to differ from the original sample only in a small and compact temporal segment. These time-contiguous perturbations allow for a much sparser and, thus, interpretable solution. Furthermore, plausibility/realism of the generated counterfactual explanations is enforced via the proposed adversarial learning strategy.