There are 2 repositories under bias-correction topic.
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"
Climate science package for Julia
Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰
A collection of bias correction techniques written in Python - for climate sciences.
Evidence-based tools and community collaboration to end algorithmic bias, one data scientist at a time.
HonestyMeter: An NLP-powered framework for evaluating objectivity and bias in media content, detecting manipulative techniques, and providing actionable feedback.
Climate Data Bias Corrector: A tool to bias correct the Global Climate Model (GCM)/ Regional Climate Model (RCM) simulated future climatic daily projections.
Tools for Modeling Niches and Distributions of Species
Examples of unfairness detection for a classification-based credit model
Short description for quick search
Master thesis: Exploring bias in German NLG (GPT-3 & GerPT-2). Applies regard classification and bias mitigation triggers.
A simple bias correction of temperature, dew point, and 10m wind speeds for the GFS, HRRR, and ECMWF models for two US locations.
Bias correction method using quantile mapping
Debiasing: Mitigating Algorithmic Facial Bias repository
Bias correction command-line tool for climatic research written in C++
Machine Learning Bias Mitigation
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".
Code accompanying the thesis project: "Understanding and Correcting Selection Bias in the Sentiments derived from Flemish Tweets".
Research POC on the mitigation of bias in large language models (FLAN-T5 and Bloomz) through fine-tuning.
Source code of age-level bias correction
Use bootstrap resampling to estimate the sampling distribution of a statistic
R package providing a shiny GUI to the functions implemented in rBiasCorrection
Novel ultrafast suite for high-throughput & high-content multiparameter screening as in drug discovery. It has unique modules for QC, bias correction, similarity measurement, clustering and visualization. It can process hundreds of samples with many markers in a few hours not days & circumvents bath effect. It couples with any plate reader.
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".
Indirect inference bias correction for nonlinear panel
Tackling Gender and Race bias in Word Embeddings
R code for generating the projected 15-min precipitation.
Deep Learning Convolutional Neural Network (CNN) using PyTorch and train it to recognize five different classes: (1) Person without a face mask, (2) Person with a “community” (cloth) face mask, (3) Person with a “surgical” (procedural) mask, (4) Person with a “FFP2/N95/KN95”-type mask (you do not have to distinguish between them), and (5) Person with a FFP2/N95/KN95 mask that has a valve. You do not have to consider other mask types (e.g., FFP3), face shields, full/half-face respirators, PPEs, or images that do not show a single face (e.g., groups of people).