AI Engineering/Phase 04/Lesson 17

Self-Supervised Vision — SimCLR, DINO, MAE

Labels are the bottleneck of supervised vision. Self-supervised pretraining removes them: learn visual features from 100M unlabelled images, fine-tune on 10k labelled ones.

Learn + Build 1.3 hr Python

Prerequisites: Phase 4 Lesson 04 (Image Classification), Phase 4 Lesson 14 (ViT)

#Learning Objectives

Trace the three major self-supervised families — contrastive (SimCLR), teacher-student (DINO), masked reconstruction (MAE) — and state what each one optimises
Implement an InfoNCE loss from scratch and explain why a batch of 512 works but a batch of 32 fails
Explain why MAE's 75% masking ratio is not arbitrary and how it differs from BERT's 15% for text
Use DINOv2 or MAE ImageNet checkpoints for linear probing and zero-shot retrieval

Full Access lesson

Keep going. The rest of this lesson is one step away.

Unlock all 503 lessons, video, code, quizzes and every future update. Pay in your own currency with Paystack.

See plans Sign in

The text and code of this lesson are based on AI Engineering from Scratch by Rohit Ghumare, MIT licensed.