by-liu / MbLS
Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430
☆48Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for MbLS
- ☆32Updated 3 years ago
- This is a code repository for paper OODformer: Out-Of-Distribution Detection Transformer☆40Updated 3 years ago
- [CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibra…☆30Updated 2 years ago
- SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise (BMVC2022)☆29Updated 2 months ago
- ISD: Self-Supervised Learning by Iterative Similarity Distillation☆36Updated 3 years ago
- (NeurIPS 2020 Workshop on SSL) Official Implementation of "MixCo: Mix-up Contrastive Learning for Visual Representation"☆58Updated last year
- [MIDL 2023] Official Imeplementation of "Making Your First Choice: To Address Cold Start Problem in Vision Active Learning"☆33Updated last year
- NeurIPS 2021, "Fine Samples for Learning with Noisy Labels"☆38Updated 2 years ago
- PyTorch implementation of "Contrast to Divide: self-supervised pre-training for learning with noisy labels"☆70Updated 3 years ago
- ☆26Updated 3 years ago
- ☆44Updated 3 years ago
- Code for ICLR2021 paper "Robust and Generalizable Visual Representation Learning via Random Convolutions"☆63Updated 3 years ago
- This repository includes the official project of L2B, from our paper "Learning to Bootstrap for Combating Label Noise".☆31Updated 4 months ago
- [NeurIPS 2022] Source code for our paper "Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data"☆22Updated last year
- ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"☆42Updated 2 years ago
- [CVPR 2022] Pytorch implementation for “Debiased Learning from Naturally Imbalanced Pseudo-Labels”☆96Updated 2 years ago
- ☆23Updated last year
- Official code for "Mean Shift for Self-Supervised Learning"☆55Updated 3 years ago
- Code release for "Cycle Self-Training for Domain Adaptation" (NeurIPS 2021)☆51Updated 2 years ago
- Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2…☆21Updated last year
- Weakly Supervised Contrastive Learning☆40Updated 3 years ago
- This is the official repo for our CVPR22 paper: Scalable Penalized Regression for Noise Detection in Learning With Noisy Labels.☆17Updated 8 months ago
- Few-shot learning with mislabeled support samples☆39Updated last year
- ☆22Updated 2 years ago
- (L2ID@CVPR2021, TNNLS2022) Boosting Co-teaching with Compression Regularization for Label Noise☆46Updated last year
- ☆29Updated 2 years ago
- Improving Calibration for Long-Tailed Recognition (CVPR2021)☆145Updated 3 years ago
- [NeurIPS 2021] “Improving Contrastive Learning on Imbalanced Data via Open-World Sampling”, Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangya…☆28Updated 2 years ago
- SKD : Self-supervised Knowledge Distillation for Few-shot Learning☆95Updated last year
- The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels (https://arxiv.org…☆21Updated 2 years ago