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

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.

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 !

Further explanation can be found here