A curated list of resources for Learning with Noisy Labels
-
Updated
May 3, 2024
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)
[ICLR2021] Official Pytorch implementation of "When Optimizing f-Divergence is Robust with Label noise"
[ICLR 2024] SemiReward: A General Reward Model for Semi-supervised Learning
“SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)
Learning to Split for Automatic Bias Detection
ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"
AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
Hard Sample Aware Noise Robust Learning forHistopathology Image Classification
Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters
AAAI 2021: Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch
Add a description, image, and links to the label-noise topic page so that developers can more easily learn about it.
To associate your repository with the label-noise topic, visit your repo's landing page and select "manage topics."