In recent years, much attention has been given to various eXplainable Artificial Intelligence (XAI) and interpretability methods. Their extension to dense prediction tasks, however, has been underexplored. Gradient-based saliency maps, highlighting feature importance in terms of input pixels, have been frequently used as fast and simple visual explanation techniques. Nonetheless, they face several problems, and the exploration of different types of attribution methods is warranted. In this paper, we investigate gradient-free semantic segmentation explanations that are based on ablating activation maps. We explore their potential for industrial applications, specifically for fruit pitting machines. We also extend the application of Ablation-CAM, a gradient-free ablation-based interpretability technique, to semantic segmentation. Finally, we discuss the sensitivity of activation maps to partial occlusions of either the foreground or the background class regions.
Ablation Studies in Activation Maps for Explainable Semantic Segmentation in Industry 4.0 / Gipiskis, R.; Chiaro, D.; Annunziata, D.; Piccialli, F.. - EUROCON 2023 - 20th International Conference on Smart Technologies, Proceedings:(2023), pp. 36-41. (Intervento presentato al convegno EUROCON 2023 - 20th International Conference on Smart Technologies) [10.1109/EUROCON56442.2023.10199094].
Ablation Studies in Activation Maps for Explainable Semantic Segmentation in Industry 4.0
Chiaro D.
;Annunziata D.;Piccialli F.
2023
Abstract
In recent years, much attention has been given to various eXplainable Artificial Intelligence (XAI) and interpretability methods. Their extension to dense prediction tasks, however, has been underexplored. Gradient-based saliency maps, highlighting feature importance in terms of input pixels, have been frequently used as fast and simple visual explanation techniques. Nonetheless, they face several problems, and the exploration of different types of attribution methods is warranted. In this paper, we investigate gradient-free semantic segmentation explanations that are based on ablating activation maps. We explore their potential for industrial applications, specifically for fruit pitting machines. We also extend the application of Ablation-CAM, a gradient-free ablation-based interpretability technique, to semantic segmentation. Finally, we discuss the sensitivity of activation maps to partial occlusions of either the foreground or the background class regions.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.