STEAL
Label correction tool
Develops a method to create high-quality training data from noisy labels in semantic segmentation tasks.
STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)
478 stars
18 watching
67 forks
Language: Jupyter Notebook
last commit: over 1 year ago annotationcvpr2019deep-learningdevil-is-in-the-edgesnv-tlabspytorchsemantic-boundariessemantic-segmentationsteal
Related projects:
Repository | Description | Stars |
---|---|---|
| This code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks. | 920 |
| Develops a robust learning framework to handle noisy labels in multimodal data and improve cross-modal retrieval. | 13 |
| A PyTorch implementation of a method for learning with noisy labels in deep neural networks | 97 |
| An open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation. | 8 |
| A PyTorch-based toolbox for building and training semantic segmentation models | 408 |
| An implementation of a regularization technique to improve the accuracy of deep learning models trained with noisy labels. | 46 |
| Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. | 71 |
| An interactive control system for text generation in multi-modal language models | 135 |
| An image denoising algorithm implementing a statistical approach to improve traditional methods | 42 |
| Improves image restoration performance by converting global operations to local ones during inference | 231 |
| A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,044 |
| A deep learning-based semantic segmentation pipeline using the Catalyst framework. | 20 |
| An implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks | 75 |
| This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. | 851 |
| A system that uses large language models to generate segmentation masks for images based on complex queries and world knowledge. | 1,923 |