Self-Supervision with FastAI
A tutorial of rotation-based self-supervision using FastAI2 & PyTorch!
self-supervised-learning fastai pytorch tutorial
Objectives & Highlights

Using self-supervision can help learn features that can transfer to a down-stream task, such as classification! In this example, we used rotation predication as our pretext task for feature representation learning. Pretraining our model on rotation prediction prior to training for classification allowed us to achieve 61.7% accuracy, on just 0.3% of the labeled data (180 samples)! Training from scratch with the same amount of data yields an accuracy of 13%. The motivation for using self-supervised learning is the ability to train models with decent accuracy without the need of much labeled data!

Don't forget to add the tag @AmarSaini in your comments.

If you are @AmarSaini, you can sign up to gain ownership of this project and edit this page.
Share this project
Similar projects
Self-Supervised Scene De-occlusion
We investigate the problem of scene de-occlusion, which aims to recover the underlying occlusion ordering and complete the invisible parts of occluded ...
The Illustrated Self-Supervised Learning
A visual introduction to self-supervised learning methods in Computer Vision
The Illustrated SimCLR Framework
A visual introduction to SimCLR: A Simple Framework for Contrastive Learning of Visual Representations.