self-adaptive-training
Generalization booster
Improves deep network generalization under noise and enhances self-supervised representation learning
[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training
127 stars
4 watching
23 forks
Language: Python
last commit: almost 5 years agoadversarial-robustnesscomputer-visiongeneralizationlabel-noisemachine-learningoverfitting
Related projects:
| Repository | Description | Stars |
|---|---|---|
 google-research/noisystudent | A semi-supervised learning method to improve the accuracy of machine learning models by using noisy teacher models and student models. | 755 |
 eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 219 |
 mit-han-lab/data-efficient-gans | Improves GAN training efficiency by incorporating data augmentation | 1,286 |
 yerevann/warp | An approach to transfer learning for NLP tasks using adversarial reprogramming and word-level task-specific embeddings. | 83 |
 ahmedfgad/neuralgenetic | Trains artificial neural networks using the genetic algorithm | 241 |
| ahmedfgad/cnngenetic | Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed. | 22 |
 tmllab/2021_neurips_pes | Improves the performance of deep neural networks by selectively stopping training at different stages | 29 |
 stormraiser/gan-weight-norm | Improves the performance of Generative Adversarial Networks by normalizing weights and batch data | 181 |
 kentonishi/augmentation-for-lnl | Provides a framework for learning with noisy labels using data augmentation strategies. | 113 |
 loudinthecloud/dpwa | A distributed learning framework that enables peer-to-peer parameter averaging and asynchronous training of deep neural networks | 53 |
 pistony/residualattentionnetwork | A Gluon implementation of Residual Attention Network for image classification tasks | 108 |
 bupt-ai-cz/meta-selflearning | Develops a method to improve performance of computer vision tasks by adapting models to new domains and data sources through meta-learning and self-learning techniques. | 199 |
 akanimax/pro_gan_pytorch | Implementation of a deep learning model for generating high-quality images with improved stability and variation. | 538 |
 gbdt-pl/gbdt-pl | An implementation of a gradient boosting algorithm with piece-wise linear regression trees for efficient machine learning model training | 151 |
 warrengreen/srcnn | Software for enhancing satellite images through deep learning techniques | 76 |