SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
Dubovik, Viktar, Struski, Łukasz, Tabor, Jacek, Rymarczyk, Dawid
–arXiv.org Artificial Intelligence
Understanding the decisions made by deep neural networks is essential in high-stakes domains such as medical imaging and autonomous driving. Yet, these models often lack transparency, particularly in computer vision. Prototypical-parts-based neural networks have emerged as a promising solution by offering concept-level explanations. However, most are limited to fine-grained classification tasks, with few exceptions such as InfoDisent. InfoDisent extends prototypical models to large-scale datasets like ImageNet, but produces complex explanations. We introduce Sparse Information Disentanglement for Explainability (SIDE), a novel method that improves the interpretability of prototypical parts through a dedicated training and pruning scheme that enforces sparsity. Combined with sigmoid activations in place of softmax, this approach allows SIDE to associate each class with only a small set of relevant prototypes. Extensive experiments show that SIDE matches the accuracy of existing methods while reducing explanation size by over $90\%$, substantially enhancing the understandability of prototype-based explanations.
arXiv.org Artificial Intelligence
Jul-28-2025
- Country:
- Europe > Poland
- Lesser Poland Province > Kraków (0.04)
- North America > United States
- Colorado > El Paso County > Colorado Springs (0.04)
- Europe > Poland
- Genre:
- Research Report > Promising Solution (1.00)
- Industry:
- Health & Medicine > Diagnostic Medicine > Imaging (0.48)
- Technology: