.png){kind=icon}
.png){kind=icon}
Return
Variational Visible Layers: A Practical Framework for Uncertainty Estimation
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-05185-1_64.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Uncertainty estimation is critical for reliable decision-making in medical imaging. State-of-the-art uncertainty methods require significant computational overhead and complex modeling. In this work, we present and explore a simple, effective approach to incorporating Bayesian uncertainty into deterministic networks by replacing the first and/or last layer (visible layers) with their variational Bayesian counterpart. This lightweight modification enables uncertainty quantification through mean-field variational estimation, making it practical for realworld medical applications. We evaluate the methods on ISIC and LIDCIDRI for the segmentation task and DermaMNIST and ChestMNIST for the classification task using post-hoc and jointly-trained visible layers. We demonstrate that variational visible layers enable uncertainty-based failure detection for both in-distribution and near-out-of-distribution samples, preserving task performance while reducing the number of variational parameters required for Bayesian estimation. We provide an easyto-implement solution for integrating uncertainty estimation into existing pipelines.
Keywords:
Uncertainty
Mean-Field Variational Inference
Bayesian
Neural Networks
Classification
Segmentation
Journal
M
IF:
0
Papers:
59
Citations:
0