Search Results for author:
Found 5 papers, 2 papers with code
Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
We first demonstrate empirically across a range of tasks and architectures that LS leads to a consistent degradation in SC.
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications.
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
The distribution of the weights of modern deep neural networks (DNNs) - crucial for uncertainty quantification and robustness - is an eminently complex object due to its extremely high dimensionality.
Learning to Generate Training Datasets for Robust Semantic Segmentation
We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models.
Packed-Ensembles for Efficient Uncertainty Estimation
Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection.
