0PricingLogin
Deep Learning Academy · Lesson

Freeze the Backbone, Train the Head

Reuse learned features cheaply.

Borrow a Smart Brain

Why train from zero? A model already trained on millions of images has learned useful features. Transfer learning reuses that knowledge for your task. 🧠

Backbone vs Head

A pretrained model has two parts: the backbone that extracts general features, and the head that makes the final prediction for its original task.

All lessons in this course

  1. Freeze the Backbone, Train the Head
  2. Fine-Tune with a Lower Learning Rate
  3. Discriminative Layer-Wise Rates
  4. Fine-Tune a Hugging Face Model
← Back to Deep Learning Academy