3

Your data set would be what is called "unbalanced' and this can lead to problems in developing an accurate classifier. The best thing to do (which you might not be able to do) is to find more images for those classes with a smaller number of images. Another alternative is to synthetically produce more images. One way to do that is to use the Keras ...


3

It is somewhat risky to discuss data independently with your learning mechanism. There is actually no such thing as good data or a good learner. There is only data that is good WITH a particular learner. That is even true of human intelligence after all the standardized education and testing done today. There are also exceptional learners that find data ...


1

I personally can’t think of any good reason to apply data augmentation before splitting the dataset, though one may exist. The issue is that if you augment first and split later, you risk introducing unwanted correlations between your training and test datasets. In the paper you linked it sounds as if the training data is all procedurally derived from the ...


1

In my personal experience, that depends. Augmenting data for training purposes is valid, and can even improve performance, as you may be aware. For testing purposes, it may be valid. Let me give you two examples when that may be the case: Facial Recognition. Imagine that you have an augmentation function that can change the face pose (left/right pose, for ...


1

So far, it seems this is more a software "integration" issue. One great tip from http://karpathy.github.io/2019/04/25/recipe/ is to visualize everything as often as you can during development. For data augmentation, try to visualize the image right before it enters your convnet. What I found is a bug can happen if your particular image transform ...


1

There are two ways that you could perform data augmentation: Up front, by expanding the input dataset into a larger one, performing a range of changes to each input then storing the result. This appears to be what you are suggesting. Just in time, by sampling from possible augmentations on each epoch, or even per sample when building a mini-batch. This ...


1

Removing the overlayed text might increase accuracy, but you'd need to train a different model to do this, and that is an entirely different task as it is no longer classification, but generation. There are easier ways to augment your data and probably get similar benefits to your accuracy. However, if you would still like to do this, there is a lot of ...


1

Yes! This is crucial. If you rotate your input images for segmentation, you need to rotate the output masks as well. Otherwise the loss of your network will not be correctly calculated and your network will not learn how to generalize to rotated input images. If you use keras, you can use two ImageDataGenerator classes, one for the images and one for the ...


1

Yes, you should label it the same. But more importantly you need to make sure that each perturbation of the image doesn't change some important character of the image. Consider training an apple classifier. If you plan to augment data by altering the RGB values, you need to be wary that you might cause issues in classification tasks where color is ...


Only top voted, non community-wiki answers of a minimum length are eligible