You don't have a million labeled images or a GPU farm — and you don't need them. Transfer learning lets you stand on a model someone else trained and reach high accuracy with a few examples in minutes. Here's the idea, visualized.
The insight
The early layers of a trained network learn general features — edges, textures, shapes — that are useful for almost any vision task. Only the last layers are task-specific. So why relearn edges from scratch?
Two ways to do it
Feature extraction: freeze the pretrained backbone, replace the final classifier with a small new "head," and train only the head on your data. Fast, needs little data.
