Reposted by @juliachae.bsky.social
Personal vision tasks–like detecting *your mug*--are hard; they’re data scarce and fine-grained.
In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos!
📝: arxiv.org/abs/2412.16156
💻: github.com/ssundaram21/...
(1/n)
