4 papers · 1 filter
Spatially-Aware Evaluation of Segmentation Uncertainty
Tal Zeevi, Eléonore V. Lieffrig, Lawrence H. Staib +1
Uncertainty maps highlight unreliable regions in segmentation predictions. However, most uncertainty evaluation metrics treat voxels independently, ignoring spatial context and ana…
GMR-Conv: An Efficient Rotation and Reflection Equivariant Convolution Kernel Using Gaussian Mixture Rings
Yuexi Du, Jiazhen Zhang, Nicha C. Dvornek +1
Symmetry, where certain features remain invariant under geometric transformations, can often serve as a powerful prior in designing convolutional neural networks (CNNs). While conv…
Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout
Tal Zeevi, Lawrence H. Staib, John A. Onofrey
Monte-Carlo (MC) Dropout provides a practical solution for estimating predictive distributions in deterministic neural networks. Traditional dropout, applied within the signal spac…
SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification
Yuexi Du, Jiazhen Zhang, Tal Zeevi +2
Convolutional neural networks (CNNs) are essential tools for computer vision tasks, but they lack traditionally desired properties of extracted features that could further improve…