loss-correction
by giorgiop
Robust loss functions for deep neural networks (CVPR 2017)
AI summary
Loss correction framework
Provides a framework for implementing robust loss functions to mitigate the effects of label noise in deep neural networks.
- stars
- 90
- forks
- 18
- watching
- 8
Similar projects
Found by comparing what the projects do, not just their names.
Loss function framework
A PyTorch-based framework for implementing normalized loss functions to improve deep learning model robustness against noisy labels.
Jaccard loss framework
A deep learning framework implementing Deeplab-resnet-101 with binary Jaccard loss surrogate, based on the Lovász hinge loss.
Neural network attribution framework
A framework for understanding how deep neural networks process input data to produce output
Image restoration framework
An image restoration framework using neural networks with interpretable and adaptive structure for diverse applications
Noisy label loss function
An implementation of a loss function designed to improve the training of deep neural networks with noisy labels
Hyperparameter optimizer
A reinforcement learning-based framework for optimizing hyperparameters in distributed machine learning environments.
Loss functions
Provides a comprehensive set of implementation of various loss functions and operators for deep learning models
Label noise correction algorithm
An implementation of an unsupervised label noise modeling and loss correction approach for deep learning.
tobypde/frrn280
Image segmentation framework
A software framework for training and evaluating full-resolution residual networks for semantic image segmentation tasks
Image distortion correction
A deep learning-based approach to correcting geometric distortions in images
Optimization framework
A software framework for training neural networks to optimize dielectric metasurfaces using physics-driven generative models and global optimization algorithms.
FL framework
A unified framework for improving privacy and reducing communication overhead in distributed machine learning models.
Data augmentation framework
Provides a framework for learning with noisy labels using data augmentation strategies.
Forgetting prevention framework
An approach to mitigating catastrophic forgetting in federated class incremental learning for vision tasks using a generative model and data-free methods
Label noise correction
A method to train deep learning classifiers on noisy labels using a small set of trusted data
