Active-Passive-Losses
Loss function framework
A PyTorch-based framework for implementing normalized loss functions to improve deep learning model robustness against noisy labels.
[ICML2020] Normalized Loss Functions for Deep Learning with Noisy Labels
134 stars
4 watching
28 forks
Language: Python
last commit: 5 months ago deep-learningdeep-neural-networksicmlicml-2020label-noisenoisy-datanoisy-labelspytorchrobust-learningunreliable-labels
Related projects:
| Repository | Description | Stars |
|---|---|---|
 coincheung/pytorch-loss | Provides a comprehensive set of implementation of various loss functions and operators for deep learning models | 2,181 |
 alanchou/truncated-loss | An implementation of a loss function designed to improve the training of deep neural networks with noisy labels | 125 |
 giorgiop/loss-correction | Provides a framework for implementing robust loss functions to mitigate the effects of label noise in deep neural networks. | 88 |
 mblondel/fenchel-young-losses | Provides Fenchel-Young losses for probabilistic classification in PyTorch/TensorFlow/scikit-learn. | 183 |
 bermanmaxim/jaccardsegment | A deep learning framework implementing Deeplab-resnet-101 with binary Jaccard loss surrogate, based on the Lovász hinge loss. | 97 |
 kengz/slm-lab | A comprehensive framework for deep reinforcement learning using PyTorch. | 1,256 |
 hitcszx/lnl_sr | An implementation of a regularization technique to improve the accuracy of deep learning models trained with noisy labels. | 46 |
 iffix/machin | An open-source reinforcement learning library for PyTorch, providing a simple and clear implementation of various algorithms. | 401 |
 ikostrikov/pytorch-ddpg-naf | An implementation of reinforcement learning algorithms for continuous control tasks using deep neural networks. | 307 |
 bes-dev/mpl.pytorch | A PyTorch implementation of a loss function used in semantic image segmentation | 175 |
 hannes-brt/hebel | A deep learning library that provides GPU acceleration and various neural network models and training methods. | 1,169 |
 xlearning-scu/2021-cvpr-mrl | Develops a robust learning framework to handle noisy labels in multimodal data and improve cross-modal retrieval. | 13 |
 kaixhin/rainbow | A Python implementation of a deep reinforcement learning algorithm combining multiple techniques for improved performance in Atari games | 1,585 |
 unslothai/hyperlearn | An optimized machine learning framework using PyTorch that improves performance and efficiency on various hardware configurations | 1,842 |
 chenpf1025/idn | Provides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels | 35 |