← Back to all news
arXiv AI By Abhishek Keripale, Ponkrshnan Thiagarajan, Susanta Ghosh

Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously

Read the original on arXiv AI →

arXiv:2606. 15479v1 Announce Type: cross Abstract: Steerable convolutional neural networks (Steerable-CNNs) guarantee SE(3)-equivariance by parameterizing kernels as linear combinations of steerable basis functions, but their deterministic nature precludes uncertainty quantification - limiting their use in settings where confidence estimates are essential.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Sep 21

Uncertainty-driven training for three-dimensional calibrated lung nodule classification

The paper introduces an uncertainty‑driven training framework for 3D CT lung nodule classification that uses validation‑based uncertainty estimates to reweight the loss, aiming to improve predictive performance and probability calibration. Two uncertainty quantification methods—Monte Carlo Dropout and Evidential Deep Learning—are evaluated across multiple backbone architectures (ResNet, DenseNet, EfficientNet, ViT, Swin) on the LIDC‑IDRI and NoduleMNIST3D datasets. The approach yields comparable classification accuracy to conventional training while substantially reducing expected calibration error, especially on convolutional backbones, and shows that simple temperature scaling can also achieve strong calibration.

By Giuseppe Tripodi, Alessandro De Rosis, Saleh Rezaeiravesh
llmscomputer-visionbenchmarks
More like this →
arXiv Machine Learning
Aug 26

It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces

arXiv:2608.24518v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-d...

By Leonhard F. Feiner, Manuel Nickel, Martin Menten, Laurin Lux, Rickmer Braren, Daniel Rueckert, Georgios Kaissis, Raphael Rehms, Johannes Paetzold
computer-vision
More like this →