activity
20242026
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Interpretability-Guided Soft Pruning of Attention Heads in Vision Transformers

Kamil KsiÄ Å¼ek, Piotr Suszyński, Michał Jan Włodarczyk +2

Vision foundation models, such as DINOv2, learn highly expressive representations but rely on massive, opaque architectures that demand substantial computational power and memory.…

cs.CV2026

What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks

Magdalena Trędowicz, Łukasz Struski, Arkadiusz Lewicki +4

Saliency maps are most useful when they identify the image regions that are sufficient to preserve a model's behaviour. We introduce SEAMS, a sufficiency-based saliency method that…

cs.CV2026

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models

Piotr Kubaty, Patryk Marszałek, Łukasz Struski +3

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they r…

cs.CV2026

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…

cs.CV2025

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence

Viktar Dubovik, Łukasz 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…

cs.CV2025

InfoDisent: Explainability of Image Classification Models by Information Disentanglement

Łukasz Struski, Dawid Rymarczyk, Jacek Tabor

In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in t…