Elenco Pubblicazioni - Publications (1524)
CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning
Written by GIANLUCA CARLONI
Deep learning image classifiers often struggle with domain shift, leading to significant performance degradation in real-world applications. In this paper, we introduce our CROCODILE framework, showing how tools from causality can foster a model’s robustness to domain…
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally,…
The aim of this paper is threefold. We inform the AI practitioner about the human visual system with an extensive literature review; we propose a novel biologically motivated neural network for image classification; and, finally,…
CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning
Written by GIANLUCA CARLONI
Deep learning image classifiers often struggle with domain shift, leading to significant performance degradation in real-world applications. In this paper, we introduce our CROCODILE framework, showing how tools from causality can foster a model’s robustness to domain…
CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning
Written by GIANLUCA CARLONI
Deep learning image classifiers often struggle with domain shift, leading to significant performance degradation in real-world applications. In this paper, we introduce our CROCODILE framework, showing how tools from causality can foster a model’s robustness to domain…
