TTA-Keras

Test-Time Augmentation is a very efficient way to improve the results of your model at testing time.

Here is how it works for a single image

After having trained our network, we can show it a test image and see it prediction.

Here is the query image :

Its prediction is :

While the true label is :

So the test image is misclassified.

But what happens if we apply TTA to that image ?

Meaning that we will show the model several slightly modified versions of the image and average its predictions.

The 5 modified images are :

And the corresponding predictions :

• Prediction 1:

• Prediction 2:

• Prediction 3:

• Prediction 4:

• Prediction 5:

By now taking the average we have:

And the image is correctly classified !

This notebook shows how to use it with Keras

Further explanation can be found here