A curated (most recent) list of resources for Learning with Noisy Labels
-
Updated
Oct 18, 2024
A curated (most recent) list of resources for Learning with Noisy Labels
Code for Simultaneous Edge Alignment and Learning (SEAL)
The official implementation of the ACM MM'21 paper Co-learning: Learning from noisy labels with self-supervision.
[ICML2022 Long Talk] Official Pytorch implementation of "To Smooth or Not? When Label Smoothing Meets Noisy Labels"
Official implementation of the ECCV2022 paper: Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
[ICLR2021] Official Pytorch implementation of "When Optimizing f-Divergence is Robust with Label noise"
Twin Contrastive Learning with Noisy Labels (CVPR 2023)
MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset
Official implementation of our NeurIPS2021 paper: Relative Uncertainty Learning for Facial Expression Recognition
Official codes for ACM CIKM '22 full paper: Towards Federated Learning against Noisy Labels via Local Self-Regularization
(L2ID@CVPR2021, TNNLS2022) Boosting Co-teaching with Compression Regularization for Label Noise
NeurIPS 2021, "Fine Samples for Learning with Noisy Labels"
(Pattern Recognition Letters 2023) PyTorch implementation of "Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer"
Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020
[ICML'2022] Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
[cvpr2023] implementation of out-of-candidate rectification methods
Code for the paper "A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise" (AAAI 2023)
[PR23] The implementation of the paper ''Learning Visual Question Answering on Controlled Semantic Noisy Labels''
Code for the KDD-2023 paper: Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler
Add a description, image, and links to the noisy-label-learning topic page so that developers can more easily learn about it.
To associate your repository with the noisy-label-learning topic, visit your repo's landing page and select "manage topics."