diegoortego / labelnoisemoit Goto Github PK

We need to remove the cosine between themselves, so the authors used the code

dist = torch.mm(features, trainFeatures) # instead of features here
dist[torch.arange(dist.size()[0]), index] = -1  ##Self-contrast set to -1

Thanks so much for your interesting work! But I can not get the same results in your paper on web noise Mini-imagenet (I have set the same hyperparameters). For red_noise_nl_0.4, I can only get 46.24 (Top-1 Accuracy of MOIT, not MOIT+). The results of other settings and the results in the paper are also very different (lower than the results in the paper). Below are the augmentations I adopted:

transforms.RandomCrop(84, padding=8),
transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.495, 0.477, 0.436), (0.292, 0.285, 0.299))

And the data of Mini-imagenet is downloaded from this URL: https://storage.googleapis.com/cnlw/dataset.zip (it is provided in LJY-HY/MentorMix_pytorch#1, which is the repo of controlled web noise in Mini-imagenet). I use the red-noise split files to get the training dataset.

If there are any other details, could you share them? Thanks again!

Hi,

Thanks for sharing the code! I have a question about how to decide the useful feature is learnt. For example, when training on cifar-10, the first 130 epochs are only trained with given label without noise correction. How to decide the "130 epochs"?

Hi,
thanks for sharing your implementation. I have two questions about it:

1. Does it also work on tabular data?
2. Is it possible to identify the noisy instances (return the noisy IDs or the clean set).

Thanks!

Thanks so much for your work. I found that in table.6 and 7 of paper, the reported number from dividemix are much lower than the original paper, any ideas for this?

Hi，thanks for your interesting work! As the paper reported, MOIT performs much better than other SOTAs on mini-WebVision dataset. Could you share the code on mini-WebVision dataset? That's will help me a lot!