ProSelfLC-AT
noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation. (by XinshaoAmosWang)
Improving-Mean-Absolute-Error-against-CCE
Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters (by XinshaoAmosWang)
ProSelfLC-AT | Improving-Mean-Absolute-Error-against-CCE | |
---|---|---|
4 | 3 | |
58 | 30 | |
- | - | |
1.8 | 0.0 | |
almost 2 years ago | over 3 years ago | |
HTML | Shell | |
GNU General Public License v3.0 or later | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ProSelfLC-AT
Posts with mentions or reviews of ProSelfLC-AT.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-11-25.
-
[R] Robust Learning: the past and present. The DNN has strong fitting capability, but we find ...
Found relevant code at https://github.com/XinshaoAmosWang/ProSelfLC-AT + all code implementations here
-
[R] ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State
Code for https://arxiv.org/abs/2207.00118 found: https://github.com/XinshaoAmosWang/ProSelfLC-AT
- [P] Easy to install, use, extend, run experiments and sink results: PyTorch Implementation for ProSelfLC-CVPR 2021
- [R] CVPR 2021-Progressive Self Label Correction (ProSelfLC) for Training Robust Deep Neural Networks
Improving-Mean-Absolute-Error-against-CCE
Posts with mentions or reviews of Improving-Mean-Absolute-Error-against-CCE.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-08-10.
-
[Research] Deep Critical Learning (i.e., Deep Robustness) In The Era of Big Data
Here are related papers on the fitting and generalization of deep learning: * ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State * Understanding deep learning requires rethinking generalization * A Closer Look at Memorization in Deep Networks * ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks * Blog link: https://xinshaoamoswang.github.io/blogs/2020-06-07-Progressive-self-label-correction/ * Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters * Derivative Manipulation: Example Weighting via Emphasis Density Funtion in the context of DL * Novelty: moving from loss design to derivative design
-
[Research] Not all our papers get published, therefore it is enjoyable to see our released papers become a true foundation for other works
Code for https://arxiv.org/abs/1903.12141 found: https://github.com/XinshaoAmosWang/Improving-Mean-Absolute-Error-against-CCE
-
[R] CVPR 2021-Progressive Self Label Correction (ProSelfLC) for Training Robust Deep Neural Networks
https://github.com/XinshaoAmosWang/Improving-Mean-Absolute-Error-against-CCE#open-reviews-and-discussion
What are some alternatives?
When comparing ProSelfLC-AT and Improving-Mean-Absolute-Error-against-CCE you can also consider the following projects:
imodels - Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Data-Efficient-Reinforcement-Learning-with-Probabilistic-Model-Predictive-Control - Unofficial Implementation of the paper "Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control", applied to gym environments
romodel - Modeling robust optimization problems in Pyomo
ProSelfLC - noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation. [Moved to: https://github.com/XinshaoAmosWang/ProSelfLC-AT]