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.
More from Research
- Critique of entropy decomposition in AI safety research — AdaptiveAgents · 2026-08-25
- Scaffold CoT: A 4M-Example Dataset Teaching Small Models to Think in a Fixed Structure — Saraozte01 · 2026-08-25
- TiDE-Ab paper introduces time-dependent guidance for antibody design — DaveJuergens · 2026-08-25
- Free open-source interactive explainer on World Models — Dooraven · 2026-08-25
- DiffSynth open-sources MiniMax-H3 LoRA training adapter and dataset — bdsqlsz · 2026-08-25
- Alibaba Releases Swift-Image: A Compact 6B Unified Text-to-Image and Editing Model — HaktanSuren · 2026-08-25