Official repo for SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation
-
Updated
May 2, 2026 - HTML
Official repo for SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation
This project quantifies the geometric and structural "break-point" of LLM representations under data corruption. Using Intrinsic Dimension and CKA mapping, it identifies the exact transformer layers where noise destroys semantic alignment and triggers Uncertainty Calibration collapse.
Hybrid ML crisis prediction; Extended Kalman Filter, LSTM, Random Forest/GBM ensemble with Bayesian uncertainty (PyQt5)
Add a description, image, and links to the bayesian-uncertainty topic page so that developers can more easily learn about it.
To associate your repository with the bayesian-uncertainty topic, visit your repo's landing page and select "manage topics."