RotNet: The Simplest Self-Supervised Learning Technique via Rotation Prediction

gabriberton · x · 2026-08-25

Introduces RotNet (2018), a minimalist self-supervised learning technique. The method involves rotating an image by 0, 90, 180, or 270 degrees and training the model to predict the rotation angle. To solve this task, the model must learn useful visual features.

Original post →

More from Research

Research channel →