EasyDeepLearn

Scaling laws for self-supervised pretraining.

hard

Answer

  • Downstream performance improves as a power law in (data, params, compute).
  • MAE / CLIP / DINOv2 / vision transformers all show emergent capabilities at scale (rare classes, zero-shot).
  • Diminishing returns: 10× more compute typically gives ~linear gain in loss.
  • Data quality matters more than quantity at very large scale (DINOv2 uses curated 142M images vs LAION's 5B).
  • Modern trend: careful data selection + scale.
Check yourself — multiple choice
  • Random
  • Power law in (data, params, compute); emergent capabilities at scale; data quality > quantity at extreme scale — DINOv2's 142M curated beats LAION's 5B
  • Same as CNN
  • Not real

SSL scaling: power law + emergence; data quality > quantity at extreme scale.

#representation-learning#theory

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions