7 papers
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
Francesco Gentile, Nicola Dall'Asen, Francesco Tonini +3
As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on acti…
MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification
Nikola JoviÅ¡iÄ, Milica Å kipina, Nicola Dall'Asen +1
Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and w…
Increasing the Utility of Synthetic Images through Chamfer Guidance
Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat +4
Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the exp…
MAMBO: High-Resolution Generative Approach for Mammography Images
Milica Å kipina, Nikola JoviÅ¡iÄ, Nicola Dall'Asen +5
Mammography is the gold standard for the detection and diagnosis of breast cancer. This procedure can be significantly enhanced with Artificial Intelligence (AI)-based software, wh…
Retrieval-enriched zero-shot image classification in low-resource domains
Nicola Dall'Asen, Yiming Wang, Enrico Fini +1
Low-resource domains, characterized by scarce data and annotations, present significant challenges for language and visual understanding tasks, with the latter much under-explored…
AL-GTD: Deep Active Learning for Gaze Target Detection
Francesco Tonini, Nicola Dall'Asen, Lorenzo Vaquero +2
Gaze target detection aims at determining the image location where a person is looking. While existing studies have made significant progress in this area by regressing accurate ga…