imbalanced-learning

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Everything about class-imbalanced/long-tail learning: papers, codes, frameworks, and libraries | 有关类别不平衡/长尾学习的一切：论文、代码、框架与库

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

A curated list of long-tailed recognition resources.

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

A collection of 85 minority oversampling techniques (SMOTE) for imbalanced learning with multi-class oversampling and model selection features

[CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427

ICDE'20 | A general & effective ensemble framework for imbalanced classification. | 泛用，高效，鲁棒的类别不平衡学习框架

[CVPR 2022] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

Parametric Contrastive Learning (ICCV2021)

Class-imbalanced / Long-tailed ensemble learning in Python. Modular, flexible, and extensible. | 模块化、灵活、易扩展的类别不平衡/长尾机器学习库

Code repository for the online course Machine Learning with Imbalanced Data

NeurIPS’20 | Build powerful ensemble class-imbalanced learning models via meta-knowledge-powered resampler. | 设计元知识驱动的采样器解决类别不平衡问题

[NeurIPS 2020] Code for the paper "Balanced Meta-Softmax for Long-Tailed Visual Recognition" on long-tailed visual recognition datasets

Cost-Sensitive Learning / ReSampling / Weighting / Thresholding / BorderlineSMOTE / AdaCost / etc.

🎲 Iterable dataset resampling in PyTorch

[ECCV 2022] Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization, and Beyond

《机器学习之类别不平衡问题》文章代码

P. Domingos proposed a principled method for making an arbitrary classifier cost-sensitive by wrapping a cost-minimizing procedure around it. The procedure, called MetaCost, treats the underlying classifier as a black box, requiring no knowledge of its functioning or change to it.

ResLT: Residual Learning for Long-tailed Recognition (TPAMI 2022)

Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Implementation of the Geometric SMOTE over-sampling algorithm.

Theano implementation of Cost-Sensitive Deep Neural Networks

SMOGN: a Pre-processing Approach for Imbalanced Regression - LIDTA2017

Final career project on PAC theory and imbalanced datasets

Implement GANs to generate time-series signals for imbalanced learning problem. The experiments are conducted using CWRU bearing data.

Building and Deploying A Serverless Text Classification Web App

The objective of this work is to develop machine learning (ML) methods that can accurately predict adverse drug reactions (ADRs) using the databases SIDER and OFFSIDES.

Approx-SMOTE: fast SMOTE for Big Data on Apache Spark

[ICML 2022] RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression