🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
imbalanced-learning 开源项目推荐(526 个)
imbalanced-learning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 526 个仓库😎 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
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
[NeurIPS 2020]半监督(无标签数据)和自我监督改善班级不平衡/长尾学习
A collection of 85 minority oversampling techniques (SMOTE) for imbalanced learning with multi-class oversampling and model selection features
[NeurIPS'25]🛠️Class-imbalanced Ensemble Learning Toolbox. | 类别不平衡/长尾机器学习库
[CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427
[ICDE'20] ⚖️ A general, efficient ensemble framework for imbalanced classification. | 泛用,高效,鲁棒的类别不平衡学习框架
Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)
[CVPR 2022] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
Code repository for the online course Machine Learning with Imbalanced Data
[NeurIPS 2020] Balanced Meta-Softmax for Long-Tailed Visual Recognition
[ECCV 2022] Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization, and Beyond
Cost-Sensitive Learning / ReSampling / Weighting / Thresholding / BorderlineSMOTE / AdaCost / etc.
[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
A repository contains a collection of resources and papers on Imbalance Learning On Graphs
Papers about long-tailed tasks
🎲 Iterable dataset resampling in PyTorch
实施GAN为不平衡学习问题生成时间序列信号。实验使用CWRU方位数据进行。
Awesome literature on imbalanced learning on graphs
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/imbalanced-learning。
- 该话题在 GitHub 上共有 526 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1 万 Star,覆盖 2 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。