Transfer Learning

What is Transfer Learning?

Transfer Learning is a technique where a model developed for a task is reused as the starting point for a model on a second task. For example, a model trained to recognize objects in millions of generic images (like ImageNet) can be fine-tuned to recognize rare diseases in medical X-rays with much less data.

Where did the term "Transfer Learning" come from?

Gained massive popularity with the success of ImageNet pre-training in computer vision (c. 2012) and later ULMFiT/BERT in NLP.

How is "Transfer Learning" used today?

The dominant paradigm in deep learning, enabling 'Foundation Models' that can be adapted to countless downstream tasks.

Related Terms