6 papers · 1 filter
BARRIER: Bounded Activation Regions for Robust Information Erasure
Jan Miksa, Patryk Krukowski, PrzemysÅaw Spurek +2
Machine unlearning has reached a critical bottleneck. As traditional weight-space interventions focus primarily on erasing targeted concepts, they often fail to prevent the uninten…
DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
Adam Wróbel, Siddhartha Gairola, Jacek Tabor +3
Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet producing stable and high-resolution attribution maps for these models remains challenging. A…
ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classification
MikoÅaj Janusz, Adam Wróbel, Bartosz ZieliÅski +1
Prototypical parts-based models offer a "this looks like that" paradigm for intrinsic interpretability, yet they typically struggle with ImageNet-scale generalization and often req…
SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
Viktar Dubovik, Åukasz Struski, Jacek Tabor +1
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 transparen…
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
MikoÅaj Sacha, Dawid Rymarczyk, Åukasz Struski +2
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accurac…
Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks
Tomasz Michalski, Adam Wróbel, Andrea Bontempelli +6
Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations based on case-based reasoning, such as "thi…