Fine-tuning in deep learning

A widely used technique for model reuse, complementary to feature extraction, is fine-tuning. Fine-tuning involves unfreezing some layers of the top layer of the frozen model library for feature extraction, and jointly training the newly added part of the model (in this case, a fully connected classifier) and these top layers. This is called fine-tuning because it slightly adjusts the more abstract representations of the model being reused, in order to make them more relevant for the problem at hand. Fine-tuning is a process to take a network model that has already been trained for a given task and makes it perform a second similar task. Assuming that the original task is similar to the new task, using a designed and trained network allows us to take full advantage of the feature extraction that occurs in the top layer of the network without having to develop a feature extraction network from scratch. It depends on the deep learning framework.