4 papers
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
Marco Mustafa Mohammed, Fatemeh Daneshfar, Pietro Liò
Evidential Deep Learning (EDL) enables single-pass uncertainty estimation by predicting Dirichlet evidence, but it can remain overconfident and poorly calibrated, and it often fail…
How Smoothing is N-simplicial Attention?
Alexandre Dussolle, Pietro Liò
Going from pure Multilayer Perceptron (MLP) to a learnable graph message-passing mechanism at each layer has been foundational to state-of-the-art results, despite the computationa…
On the Sheafification of Higher-Order Message Passing
Jacob Hume, Pietro Liò
Recent work in Topological Deep Learning (TDL) seeks to generalize graph learning's preeminent paradigm to more complex relational structures: simplicial comple…
UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation
Tangqi Shi, Pietro Lio
Background: Breast and thyroid cancers pose an increasing public-health burden. Ultrasound imaging is a cost-effective, real-time modality for lesion detection and segmentation, ye…