Explainable Event Recognition
This work addresses the need for interpretability in event recognition for users relying on AI decisions, though it is incremental as it applies existing explainability methods to a specific domain.
The authors tackled the problem of understanding why CNN models make decisions in event recognition by proposing an explainable framework using Grad-CAM and Xception, achieving F1-scores of 0.91 to 0.97 across datasets and showing that 78% to 84% of decisions are based on event-related objects or regions.
The literature shows outstanding capabilities for CNNs in event recognition in images. However, fewer attempts are made to analyze the potential causes behind the decisions of the models and exploring whether the predictions are based on event-salient objects or regions? To explore this important aspect of event recognition, in this work, we propose an explainable event recognition framework relying on Grad-CAM and an Xception architecture-based CNN model. Experiments are conducted on three large-scale datasets covering a diversified set of natural disasters, social, and sports events. Overall, the model showed outstanding generalization capabilities obtaining overall F1-scores of 0.91, 0.94, and 0.97 on natural disasters, social, and sports events, respectively. Moreover, for subjective analysis of activation maps generated through Grad-CAM for the predicted samples of the model, a crowdsourcing study is conducted to analyze whether the model's predictions are based on event-related objects/regions or not? The results of the study indicate that 78%, 84%, and 78% of the model decisions on natural disasters, sports, and social events datasets, respectively, are based onevent-related objects or regions.