Contrastive learning: two augmentations are a positive pair, every other image is a negative, and InfoNCE does the rest

1Key Takeaways

• Supervised learning is spectacular, but it runs on labels, and labels are slow, costly and scarce.
• Meanwhile the internet is a bottomless well of un*labelled images.
• Contrastive learning — the heart of SimCLR — learns a genuinely useful representation with **no labels at all , from one deceptively simple idea.
• I built a demo that trains a real encoder live in the browser on the true InfoNCE loss, where the labels are used *only to colour the dots and never touch the loss, so you can literally….