Abstract: Transfer Learning for Fun and Profit
Transfer learning is exciting because it unlocks solutions that weren’t feasible a few years ago. In fact, choices to compose from pre-trained models for computer vision tasks became abundant. In this talk, we will explore how to make these choices for image classification and feature extraction.
The analysis is inspired by practical use-cases where human supervision and compute time is often limited. The results are presented for two datasets across PyTorch’s model-zoo. First, a toy dataset where scale invariance is important. Second, a dataset from an object detection pipeline where rotation invariance is important. Lastly, we will cover the human success factors of such a project. Accompanying code is available at: https://github.com/
Alexander Hirner is industrial engineer with the conviction to make humans smarter with computers and vice versa. He developed machine learning solutions for unstructured data while studying in Silicon Valley and Europe. In 2014 he founded Ethereum Vienna, a blockchain 2.0 meetup. His ongoing research interest in frictionless data-markets is at the intersection those two technologies.