A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"

Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰

A collection of bias correction techniques written in Python - for climate sciences.

Climate Data Bias Corrector: A tool to bias correct the Global Climate Model (GCM)/ Regional Climate Model (RCM) simulated future climatic daily projections.

Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.

Comparison of weather station and gridded climate datasets

Short description for quick search

Bias correction method using quantile mapping

Scan your AI/ML models for problems before you put them into production.

This repository contains the main ResNet backbone experiments conducted in the ICLR 2022 spotlight paper "On the Importance of Firth Bias Reduction in Few-Shot Classification".

Applying a BiC class incremental learning model on Distributed optical fiber acoustic sensing signal pattern recognition.

Source code of age-level bias correction

Intrinsic bias estimation for improved analysis of bulk and single-cell chromatin accessibility profiles using SELMA

Magnetic Resonance Imaging data processing pipelines with a strong emphasis on the diffusion weighted MRI (DWI) modality and tractogram estimation

A cost-sensitive BERT that handles the class imbalance for the task of biomedical NER.

Use bootstrap resampling to estimate the sampling distribution of a statistic

This repository contains the firth bias reduction experiments on the few-shot distribution calibration method conducted in the ICLR 2022 spotlight paper "On the Importance of Firth Bias Reduction in Few-Shot Classification".

Pytorch implementation of 'Explaining text classifiers with counterfactual representations' (Lemberger & Saillenfest, 2024), ECAI 2024 - 27th European conference on AI

This repository contains two methods to address bias to missing pixels in methane plume detection CNNs. Our methods are transferable to other tasks.