-
Notifications
You must be signed in to change notification settings - Fork 174
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
Really performs worse when number of classes are High #73
Comments
That's interesting you find it's not working. We were able to reach ~state of the art accuracy at the time on semi supervised CIFAR-100 (with 100 classes) and ImageNet (with 1000 classes). What are you trying? |
Hi, I guess it performs well or SOTA on Semi SL benchmarks not conventional with more label data per class. I am working on a classification task with ~2000 classes, I tried with 400 images per class which gave me an supervised accuracy of 48.85%. I am not sure how to tackle this problem I have. I don't have much labelled data (400 per class) and have been stuck for 2 months now. |
Sorry I don't really follow what you're saying here. You have 2000 classes, and with 400 images per class you get 48.8% accuracy. Is this with FixMatch? "If this is worse" than what? And how does pseudo labeling enter into here? And why do you need a more complex model? How much unlabeled data do you have if you have 400 labeled images per class? |
OK.Let me put it simply. I have 2000 classes with 400 labelled images per class and I have ~600 non labelled images per class (some from net other augmented from labelled) I got 48.8% on running fixmatch.py file. |
What accuracy does fully supervised training on these images give, ignoring the unlabeled data? |
I did not did that, but now I have it. Its gives 84.27% with 15-85 split. Pure supervised on labelled. I have used transfer learning - Dense Net. |
Supposing you don't use transfer learning, what accuracy do you get? The thing I'm trying to understand is this: supervised learning will strictly out-perform semi-supervised learning given the same number of labeled examples. If your task is just hard, it's entirely reasonable that FixMatch might just actually not reach very high accuracy. |
This algorithm really performs worse when number of classes are high like around 100, which is most of the time the case.
At that time, we need more images per class and as we increase labels it almost reaches to normal models image per class requirement.
Really wasted my time on this.
The text was updated successfully, but these errors were encountered: