xjtushujun's repositories
meta-weight-net
NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).
Meta-weight-net_class-imbalance
NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for class imbalance).
Multitask-Learning
Multitask Learning Resources
SLeM-Theory
The implementation of meta-regularization proposed in SLeM theory paper "Learning an Explicit Hyper-parameter Prediction Function Conditioned on Tasks".
Probabilistic-MW-Net
TNNLS2021: A Probabilistic Formulation for Meta-Weight-Net (Pytorch implementation for noisy labels)
Awesome-NAS
A curated list of neural architecture search (NAS) resources.
Advances-in-Label-Noise-Learning
A curated (most recent) list of resources for Learning with Noisy Labels
Awesome-Knowledge-Distillation
Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
Best-Incremental-Learning
An Incremental Learning, Continual Learning, and Life-Long Learning Repository
Class-Imbalance
Cost-Sensitive Learning / Resampling / SMOTE etc.
deep-value-networks-pytorch
Structured Prediction with Deep Value Networks (PyTorch implementation)
DivideMix
Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning
fixmatch
A simple method to perform semi-supervised learning with limited data.
higher
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
In-Context-Learning_PaperList
Paper List for In-context Learning 🌷
junshu.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
label_smoothing_pytorch
pytorch implement of Label Smoothing
machine-learning-notes
My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (1500+ slides) 我不间断更新的机器学习,概率模型和深度学习的讲义(1500+页)和视频链接
MetaLearningPapers
A classified list of meta learning papers based on realm.
mixupfamily
The implementation of mixup and mainfold mixup method with standard models(PreActRes, WideRes, Dense) in Cifar10, Cifar100 and SVHN dataset on supervised(sl) and semi-supervised(ssl) tasks.
NARL-Adjuster
This is an official PyTorch implementation of Improve Noise Tolerance of Robust Loss via Noise-Awareness
pytorch-maml
An Implementation of Model-Agnostic Meta-Learning in PyTorch with Torchmeta
TANS
This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).