#
Starred repositories
The best repository showing why transformers might not be the answer for time series forecasting and showcasing the best SOTA non transformer models.
A curated publication list on evidential deep learning.
Large-scale uncertainty benchmark in deep learning.
A repository related to the paper 'Evaluating Reliability in Medical DNNs: A Critical Analysis of Feature and Confidence-Based OOD Detection'
Uncertainty-aware representation learning (URL) benchmark
A professionally curated list of awesome Conformal Prediction videos, tutorials, books, papers, PhD and MSc theses, articles and open-source libraries.
A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Training and Tuning Strategies for Foundation Models in Medical Imaging
A Benchmark for Failure Detection under Distribution Shifts in Image Classification
Segment Anything in Medical Images
A Python toolbox for conformal prediction research on deep learning models, using PyTorch.
This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classifiers".
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).
Codebase for "Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection", published at WACV 2024.
Code for "Efficiently Controlling Multiple Risks with Pareto Testing"
mibaumgartner / MONAI
Forked from Project-MONAI/MONAIAI Toolkit for Healthcare Imaging
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
Conformal prediction for controlling monotonic risk functions. Simple accompanying PyTorch code for conformal risk control in computer vision and natural language processing.
Repository for the paper "TriadNet: Sampling-free predictive intervals for lesional volume in 3D brain MR images"
nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that …
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on d…
[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification
Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.
Code for the paper "Calibrating Deep Neural Networks using Focal Loss"
Calibration of Convolutional Neural Networks
High-quality implementations of standard and SOTA methods on a variety of tasks.
The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.