4 votes

How does rotating an image and adding new 'rotated classes' prevent overfitting?

How can data augmentation reduce overfitting? You write that you can already maybe see how data augmentation can help prevent overfitting in general, but it sounds a bit uncertain and it's still ...
  • 9,794
4 votes
Accepted

Does the term "data augmentation" imply increasing the training dataset?

I'm not familiar with any "authoritative" single definition somewhere, or not sure who used the term first, but I would personally indeed agree with the reviewer you mention. In fact I've ...
  • 9,794
3 votes

Would this relatively small dataset be enough to train a CNN?

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 ...
  • 694
3 votes

Would this relatively small dataset be enough to train a CNN?

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 ...
2 votes
Accepted

What is the effect of training a neural network with randomly generated fake data that satisfies certain constraints?

This is not advisable. If you train your model with random data your model is not learning anything useful, because there is no information to gain from those examples. Even worse it may (and likely ...
2 votes

Is data augmentation beneficial even if the dataset is large/diverse enough?

You are going to generate the images by flipping, rotating, etc. which will happen anyways in augmentation. Augmentation can happen on the fly so you don't waste memory storing those new images, thus, ...
2 votes

How does rotating an image and adding new 'rotated classes' prevent overfitting?

Over-fitting in the context of convergence in a neural network can have many causes. When the model implied in the design of the network is not well fitted for the task, the network may still ...
1 vote

Why does data augmentation using synthetic data generated by one model improve the performance of another model?

The reasoning behind synthetic data is the same behind classic data augmentation,so the goal is to increase the amount of training instances to improve generalization. The difference with classic data ...
1 vote

What is the effect of training a neural network with randomly generated fake data that satisfies certain constraints?

If you add fake samples to the training set, your Neural Network learns new dataset that you just made, your fake samples are estimations so you add noise to your training set. you can use Leave one ...
  • 185
1 vote

Can I shuffle data for delivery duration forecast problem?

As a rule of thumb, you not just should but you must shuffle your training instances always. You just need to pay attention to not be fooled in regard to what a training instance is in your specific ...
1 vote

Can I shuffle data for delivery duration forecast problem?

Yes, shuffling the dataset is in fact, an important step in the process. Shuffling help in reducing overfitting to a particular pattern and generates more 'randomness' to the data, hence helping the ...
1 vote

Is data augmentation inducing bias?

You are right you should apply the augmentation after splitting. The goal of the validation data is to assess the results on data that has not been seen during training. When doing so you way have ...
1 vote
Accepted

How to preserve Markov Property in Deep Reinforcement Learning when using "mixup" or "mixreg"?

Because each environment individually satisfies the Markov property, the distribution of the next state $s_{t+1}$ in any transition depends only on $s_t$, $a_t$, and the transition probabilities of ...
1 vote
Accepted

How to label edited images after data augmentation?

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 ...
1 vote

Is using separate channels of a RBG image a valid data augmentation technique?

Neil is right, data augmentation is suppose to add data that respect the same distribution as the original data. Grayscale is a linear combination of individual channel, therefore the single channels ...
1 vote
Accepted

What exactly is data augmentation?

Data augmentation typically refers to the creation of new (training) data/instances (e.g. images) by e.g. modifying existing training/instances data in order to avoid over-fitting and improve the ...
  • 37k
1 vote

Train Validation Test Splitting After or Before Data Augmentation?

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 ...
  • 36
1 vote

Train Validation Test Splitting After or Before Data Augmentation?

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 ...
1 vote
Accepted

Data augmentation for very small image datasets

In my opinions, you have around $25\times 20 \times 2 + 5 \times 20 = 1100$ samples, so the list of problems is: Lack of data Imbalance between class 1,2 and class 3 With the simple task, the model ...
  • 882
1 vote

Is creating dataset only by augmentation a bad practice?

Data augmentation is usually rotating, cropping and translating images. And this makes sense if your network could meet these kind of images. If I take a digit recognition like LeNet, it is useless to ...
  • 211
1 vote

Should one rescale (normalize) image before or after data augmentation?

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 ...
1 vote
Accepted

What is the difference between feature extraction with or without data augmentation?

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 ...
  • 26.5k
1 vote
Accepted

Should I remove the text overlaying some images in the dataset before training the CNN?

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. ...
  • 1,316
1 vote
Accepted

Do I need to rotate the masks, if I also rotate the images and the masks are generated from the input?

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 ...
  • 600

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