Transfer Learning

By Prof. Seungchul Lee
Industrial AI Lab at POSTECH

Table of Contents

1. Pre-trained Model (VGG16)ΒΆ

  • Training a model on ImageNet from scratch takes days or weeks.
  • Many models trained on ImageNet and their weights are publicly available!
  • Transfer learning
    • Use pre-trained weights, remove last layers to compute representations of images
    • The network is used as a generic feature extractor
    • Train a classification model from these features on a new classification task
    • Pre- trained models can extract more general image features that can help identify edges, textures, shapes, and object composition
    • Better than handcrafted feature extraction on natural images