julilien / LabelRelaxation
Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.
☆14Updated last year
Alternatives and similar repositories for LabelRelaxation:
Users that are interested in LabelRelaxation are comparing it to the libraries listed below
- PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018☆126Updated 5 years ago
- Meta Label Correction for Noisy Label Learning☆85Updated 2 years ago
- [NeurIPS 2017] [ICML 2019] Code for complementary-label learning☆48Updated last year
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆86Updated 2 years ago
- [ICLR 2021] Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization☆41Updated 3 years ago
- AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise☆36Updated 3 years ago
- ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"☆43Updated 2 years ago
- ☆32Updated 4 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 3 years ago
- ☆12Updated 3 years ago
- [NeurIPS 2021] “Improving Contrastive Learning on Imbalanced Data via Open-World Sampling”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangya…☆28Updated 3 years ago
- A new code framework that uses pytorch to implement meta-learning, and takes Meta-Weight-Net as an example.☆59Updated 3 years ago
- Adjust Decision Boundary for Class Imbalanced Learning☆19Updated 4 years ago
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 4 years ago
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆56Updated 2 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆84Updated 9 months ago
- code for paper Decoupling "when to update" from "how to update" [https://arxiv.org/abs/1706.02613]☆21Updated 7 years ago
- ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust☆15Updated 4 years ago
- Code release for Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning (NeurIPS 2019)☆24Updated 3 years ago
- infinite mixture prototypes for few-shot learning☆51Updated 2 years ago
- ☆19Updated 6 years ago
- Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/211…☆50Updated 2 years ago
- NeurIPS 2020, "A Topological Filter for Learning with Label Noise".☆30Updated 2 weeks ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆32Updated 5 years ago
- PyTorch implementation of our ECCV 2022 paper "Rethinking Confidence Calibration for Failure Prediction"☆24Updated last year
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 2 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆84Updated 5 years ago
- ☆30Updated 3 years ago
- The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels (https://arxiv.org…☆22Updated 3 years ago
- PyTorch implementation of the paper "SuperLoss: A Generic Loss for Robust Curriculum Learning" in NIPS 2020.☆30Updated 4 years ago