Open-source alternatives to Nested Co Teaching

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

WACV'21: Do We Really Need Gold Samples for Sample Weighting Under Label Noise?

Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020

Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)

Auxiliary Image Regularization for Deep CNNs with Noisy labels at ICLR 2016

Official PyTorch implementation of "From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model" (ICML 2022) by HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon.

This repository contains the pytroch code to reproduce the results the paper "Wasserstein Adversarial Regularization for Learning with Label Noise"

This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers, CVPR 2022

NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

NeurIPS'18: Masking: A New Perspective of Noisy Supervision

ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust

The code for our WACV 2023 submission "Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels".

SREA: Self-Re-Labeling with Embedding Analysis

Official cleanlab repo is at https://github.com/cleanlab/cleanlab

🧹 Formerly for binary classification with noisy labels. Replaced by cleanlab.

AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

AAAI 2021: Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels