5 papers
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…
Equivariant Imaging Biomarkers for Robust Unsupervised Segmentation of Histopathology
Fuyao Chen, Yuexi Du, Tal Zeevi +2
Histopathology evaluation of tissue specimens through microscopic examination is essential for accurate disease diagnosis and prognosis. However, traditional manual analysis by spe…
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…
Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
Tal Zeevi, Ravid Shwartz-Ziv, Yann LeCun +2
Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique fo…