-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
questions about performances #4
Comments
Thanks for your question! Iterating on the dataset is really a good idea. Although we did not try this on the PGDF before, our previous work [1] did a similar thing through this intuition. You can refer to Fig. 9 in the work [1]. In work [1], the experiment is set on a low noise ratio (20%) and after the first processing of the original dataset, the noise ratio is decreased to a quite low value (<1%). As a result, iterations bring very little performance gain. But I think it may work in the heavy noise scenario. Our team's further research may work on this. Reference: |
Hi ;) I think by changing with another model in each iterations (resnet, vit, mobilenet, clip, etc.) can improve too ! I know that each model has its own "perception of vision". The more they will be different, the more the perception are different. Another proposition is to change SGD optimizers by Adam or Adabelief (faster convergence, better convergence). Would you be interested that I work on it with you ? |
Moreover, I think for better warmup convergence, using early stopping could increase your results. As I see you have fixed a variable to set the number of warmup_step. It could be better to use the best checkpoint on val to go on the second step training. With this you will have a "soft-parameter" than an "hard parameter". |
Another thing, |
Hi, Your ideas are very interesting and impressive! Thanks a lot for your reply and invitation. However, I will graduate and start working in a company next month, so I may not have enough time to work on it in the future. Thanks again for your kindness and wish you success in your research 😊. |
Another tip, I have a question: when you talk about cifar10-sym90, you say that 10% only is good labeled and 90% is random label from the 10 classes ? If it is yes, I imagine that your work could label all type of image classification without any data labeled ! so Maybe trying to handle the problem with any labeled data could be a good think to test. If you are confident about this, the only problem should be to match on val the outputs by selecting the outputs based on the val.. If it not works maybe by doing some self-supervised learning like one of the last papers should help. I think that open your future work to text classification and to tabular data, should make some noise in the domain. |
The answer is yes. But when the noise ratio is at a high level, the performance becomes unstable. It is a common issue in many LNL algorithms. And work [1] mentioned that pretraining the model weight by contrast learning can significantly achieve performance gain. You can also try on this. Reference: [1] Zheltonozhskii, Evgenii, et al. "Contrast to divide: Self-supervised pre-training for learning with noisy labels." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022. |
I would try another thing |
Another thing (sorry for disturbing);
prob_gmm is a probability of app appartenance. |
For args.md maybe trying:
|
on the lines |
It should be better to not use this on hyperparmeter
but more a LrScheduler like these: |
In definitive , the less hyperparameters you will have, the more stable your results will be. |
Thanks again for your helpful advice! 👍 I wish your research goes well! |
Hello Guys,
First of all congratulations for your work! :)
I have a question:
I could see that your performance on Cifar10:
Would you have tried on 80% noise/ratio of:
1- run the script to get your benchmark as usual
2- saved the whole dataset with the modified labels
3- restarted the script with this modified dataset?
I haven't read all of your paper yet, so it's possible you realized that. If not, do you think the performance would increase even more?
As I can see with 80% of noise label you have finally 82,5% off accuracy... It seems that it could be near the problem of a 20% noise/ratio finally... I know the problem is more difficult than that, so my question is "does iterating improve performance even more?" All based on the new initialisation of model weights..
Thanks a lot
In any case, congratulations! Your paper is superb and your code very clear.
The text was updated successfully, but these errors were encountered: