4 papers
COGENT: Counterfactual Gaussian Explanations for Volumetric Medical Images
Dorian Rząsa, Bartosz Zabdyr, Krzysztof Piekarz +7
Explainability is essential for deploying deep learning models in high-stakes medical applications. Existing explainability methods for volumetric imaging predominantly operate in…
Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers
Jakub Grzywaczewski, Dawid PÅudowski, PrzemysÅaw Biecek
Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural anomalies and act as repositor…
Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
Bartlomiej Sobieski, Jakub Grzywaczewski, Karol Dobiczek +6
Lung cancer remains the leading cause of cancer mortality, driving the development of automated screening tools to alleviate radiologist workload. Standing at the frontier of this…
Rethinking Visual Counterfactual Explanations Through Region Constraint
Bartlomiej Sobieski, Jakub Grzywaczewski, Bartlomiej Sadlej +2
Visual counterfactual explanations (VCEs) have recently gained immense popularity as a tool for clarifying the decision-making process of image classifiers. This trend is largely m…