MIT researchers have developed StableRep, an AI training method using synthetic images generated by text-to-image models, which surpasses traditional training on real images. The approach leverages multi-positive contrastive learning, promising more efficient, less biased, and resource-conscious machine learning development.
This is a companion discussion topic for the original entry at https://news.mit.edu/2023/synthetic-imagery-sets-new-bar-ai-training-efficiency-1120