Supervision means training a model using labeled data. You show it two pictures—one labeled as “cat” and the other not labelled as “cat”. The model learns to recognize pictures with cats.
Self-supervision means learning directly from the input data itself. Take the phrase: “Sky is blue and beautiful.” The model treats it as a training sequence: 1. Sky; 2. Sky is; 3. Sky is blue; 4. Sky is blue and; 5. Sky is blue and beautiful. It learns patterns and context without explicit labels, learns even from inputs.
Sources:
AI Engineering by Chip Huyen (O’Reilly). Copyright 2025 Developer Experience Advisory LLC, 978-1-098-16630-4