121 citations · 338 across the 25 of their papers we have counts for
4 papers · 2 filters
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Adam Pardyl, Siddhartha Gairola, Sukrut Rao +4
Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those…
BARRIER: Bounded Activation Regions for Robust Information Erasure
Jan Miksa, Patryk Krukowski, Przemysław Spurek +2
Machine unlearning aims to remove targeted concepts from a trained model while preserving the rest of its knowledge. Central challenge of this setting is that effective and robust…
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
Mikołaj Janusz, Adam Wróbel, Bartosz Zieliński +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…