chenpf1025 / IDNLinks
AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
☆35Updated 4 years ago
Alternatives and similar repositories for IDN
Users that are interested in IDN are comparing it to the libraries listed below
Sorting:
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆38Updated 4 years ago
- Meta Label Correction for Noisy Label Learning☆87Updated 3 years ago
- ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"☆45Updated 3 years ago
- An update-to-date list for papers related with label-noise representation learning is here.☆90Updated 4 years ago
- PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018☆130Updated 6 years ago
- [AAAI 2021] Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning☆139Updated 5 years ago
- ICLR‘2021: Robust Early-learning: Hindering the Memorization of Noisy Labels☆78Updated 4 years ago
- Official code for the paper "Meta Soft Label Generation for Noisy Labels" accepted at ICPR 2020.☆21Updated 5 years ago
- This repository is used to record current noisy label paper in mainstream ML and CV conference and journal.☆36Updated 4 years ago
- ☆17Updated 2 years ago
- NeurIPS 2021, "Fine Samples for Learning with Noisy Labels"☆40Updated 4 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆90Updated 6 years ago
- A new code framework that uses pytorch to implement meta-learning, and takes Meta-Weight-Net as an example.☆62Updated 4 years ago
- CVPR'20: Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization☆127Updated 2 years ago
- [NeurIPS 2017] [ICML 2019] Code for complementary-label learning☆50Updated 4 months ago
- CVPR 2022: Selective-Supervised Contrastive Learning with Noisy Labels☆95Updated 3 years ago
- [AAAI 21] Utilizing meta-learning to correct the noisy labels.☆15Updated 4 years ago
- Code for CVPR2020 ‘Training Noise Robust Deep Neural Networks via Meta-Learning’☆20Updated 5 years ago
- [ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels☆141Updated last year
- Official Implementation of Robust Training under Label Noise by Over-parameterization☆65Updated 3 years ago
- PyTorch implementation of PiCO https://arxiv.org/abs/2201.08984☆225Updated last year
- [CVPR'22] Official Implementation of the CVPR 2022 paper "UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learnin…☆63Updated last year
- Code for the paper "Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning" (NeurIPS 20)☆75Updated 3 years ago
- Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020☆23Updated 5 years ago
- NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).☆291Updated 4 years ago
- PyTorch implementation of the paper "SuperLoss: A Generic Loss for Robust Curriculum Learning" in NIPS 2020.☆29Updated 4 years ago
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆35Updated 4 years ago
- Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning☆101Updated last year
- PyTorch implementation of consistency regularization methods for semi-supervised learning☆79Updated 5 years ago
- ☆17Updated 3 years ago