I'm having a hard time trying to find a good explanation of the process of Joint Training in Neural Networks. I already understand the concepts of Fine Tuning and Feature Extraction, and i know it has to do with the practice of taking a network model that has already been trained for a given task, and make it perform a second similar task.
You are incorrect that is called Transfer learning, which focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.
Joint Training is basically when the neural network trains on several different task simultaneously so optimizing more than one loss function rather than one loss function as the case with Transfer learning.
It is also called Multi task learning.
Refer this article to know more.