A curated list of resources for Learning with Noisy Labels

A curated (most recent) list of resources for Learning with Noisy Labels

Human annotated noisy labels for CIFAR-10 and CIFAR-100. The website of CIFAR-N is available at http://www.noisylabels.com/.

[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels

[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training

The official implementation of the ACM MM'21 paper Co-learning: Learning from noisy labels with self-supervision.

[CVPR 2021] Code for "Augmentation Strategies for Learning with Noisy Labels".

[ICML2022 Long Talk] Official Pytorch implementation of "To Smooth or Not? When Label Smoothing Meets Noisy Labels"

Tensorflow source code for "CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise" (CVPR 2018)

“SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)

[ICLR 2024] SemiReward: A General Reward Model for Semi-supervised Learning

[ICLR2021] Official Pytorch implementation of "When Optimizing f-Divergence is Robust with Label noise"

Learning to Split for Automatic Bias Detection

ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"

Hard Sample Aware Noise Robust Learning forHistopathology Image Classification

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

Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters

Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch

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

[CIKM-2024] Official code for work "ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance"