code for MICCAI 2019 paper 'Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation'.

Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes [NeurIPS2021]

Code for the paper "Calibrating Deep Neural Networks using Focal Loss"

Example docker containers for the WMH Segmentation Challenge

A collection of loss functions for medical image segmentation

Code for the paper "Test-time adaptable neural networks for robust medical image segmentation"

Local Temperature Scaling for Probability Calibration

Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)

A simple way to calibrate your neural network.

Efficient representation for assessment of model calibration in machine learning / deep learning

Official repository for CVPR2022 publication, ViM: Out-Of-Distribution with Virtual-logit Matching

[CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration"

[MICCAI'22] Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift

High-quality implementations of standard and SOTA methods on a variety of tasks.

[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2211.15088

Official PyTorch implementation of "CASS: Class-wise Adaptive Strategy for Semi Supervised Semantic Segmentation", IEEE Access 2024

[CVPR 2023] Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection

Bayesian Inference of Slide-level Confidence via Uncertainty Index Thresholding

[ICLR2021 Oral] Free Lunch for Few-Shot Learning: Distribution Calibration

Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models

[ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging

Code for "Dual Focal Loss for Calibration" (ICML 2023)

Adaptive Early-Learning Correction for Segmentation from Noisy Annotations (CVPR 2022 Oral)