Your question is MoCo and Contrastive Learning. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
Explain the MoCo (Momentum Contrast) self-supervised model and how it relates to the contrastive models (BYOL, SimCLR, SwAV) you used.
Asked in the round 3 stage. Asked as a deep dive on the candidate's internship project; category approximates ML theory.