Tweeted By @ylecun
The best SSL approaches to learning visual features today use Siamese networks to learn embeddings.
— Yann LeCun (@ylecun) January 14, 2020
Examples: two recent papers from FAIR, "Pretext-Invariant Representation Learning" (Misra et al.) and "MoCo" (He et al.). https://t.co/dYStkWA6Nw