AlanChou / Truncated-Loss
PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018
☆126Updated 5 years ago
Alternatives and similar repositories for Truncated-Loss:
Users that are interested in Truncated-Loss are comparing it to the libraries listed below
- CVPR'20: Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization☆126Updated last year
- [ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels☆136Updated 8 months ago
- Reproduce Results for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels" https://arxiv.org/abs/1908.06112☆186Updated 4 years ago
- Code for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels"☆170Updated 3 years ago
- Meta-Learning based Noise-Tolerant Training☆123Updated 4 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆84Updated 5 years ago
- Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"☆153Updated 4 years ago
- When Does Label Smoothing Help?_pytorch_implementationimp☆125Updated 5 years ago
- Official Implementation of ICML 2019 Unsupervised label noise modeling and loss correction☆222Updated 4 years ago
- Code for CoMatch: Semi-supervised Learning with Contrastive Graph Regularization☆127Updated 3 years ago
- PyTorch implementation of consistency regularization methods for semi-supervised learning☆78Updated 4 years ago
- Improving Calibration for Long-Tailed Recognition (CVPR2021)☆147Updated 3 years ago
- PyTorch implementation of Probabilistic End-to-end Noise Correction for Learning with Noisy Labels, CVPR 2019.☆139Updated 5 years ago
- [AAAI 2021] Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning☆138Updated 4 years ago
- "In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning" by Mamshad Nayeem Riz…☆234Updated last year
- ☆130Updated 2 years ago
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆33Updated 4 years ago
- Meta Label Correction for Noisy Label Learning☆85Updated 2 years ago
- ICML 2019: Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels☆90Updated 4 years ago
- PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"☆71Updated 3 years ago
- Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)☆103Updated 3 years ago
- Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)☆147Updated 2 years ago
- Unofficial PyTorch Implementation of Unsupervised Data Augmentation.☆146Updated 4 years ago
- ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"☆43Updated 2 years ago
- Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)☆96Updated 3 years ago
- Official Implementation of Early-Learning Regularization Prevents Memorization of Noisy Labels☆295Updated last year
- SwAV for CIFAR-10, adapted from https://github.com/facebookresearch/swav☆28Updated 3 years ago
- "Automatically Discovering and Learning New Visual Categories with Ranking Statistics" by Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Eh…☆227Updated 5 years ago
- MoPro: Webly Supervised Learning☆87Updated 4 years ago
- NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).☆286Updated 3 years ago