Co-teaching
Noisy label training method
Develops a robust training method for deep neural networks using noisy labels
NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
494 stars
12 watching
105 forks
Language: Python
last commit: about 4 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| | This project implements a PyTorch-based co-teaching algorithm to improve generalization against label corruption in machine learning. | 21 |
| | An implementation of Masking, a method to improve the robustness of deep neural networks under noisy supervision | 54 |
| | A comprehensive resource for machine learning and deep learning algorithms | 295 |
| | A comprehensive C programming project covering various algorithms and data structures | 749 |
| | An implementation of dimensionality-driven learning with noisy labels using deep neural networks and various optimization techniques. | 58 |
| | An implementation of training deep neural networks on noisy labels with bootstrapping using Keras | 22 |
| | Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed. | 22 |
| | An open-source software project providing tools and examples for building machine learning models in Java | 13 |
| | A small neural network implementation of the backpropagation algorithm in Haskell | 127 |
| | A library implementing a learning algorithm for improving classification accuracy with incremental updates and ensemble methods using neural networks | 2 |
| | Trains artificial neural networks using the genetic algorithm | 241 |
| | A deep learning framework for instance co-segmentation and object colocalization | 137 |
| | An implementation of an algorithm for learning trajectory representations in temporal graphs | 18 |
| | A collection of tutorials and resources on implementing deep learning models using Python libraries such as Keras and Lasagne. | 426 |
| | An implementation of a pooling technique for multimodal neural networks in Torch7 | 69 |