
Interesting research to come out of Google on using language understanding in image models
Andreas Steiner@AndreasPSteiner
LiT-tuned models combine powerful pre-trained image embeddings with a contrastively trained text encoder. Check out our blogpost goo.gle/3KJT6u1 and the 🔥 interactive demo ↓↓↓ #lit_demo #v1|tiny|1|an%20ipod|a%20sticker%20with%20the%20text%20ipod|an%20apple%20with%20a%20sticker%20with%20the%20text%20ipod|an%20apple|a%20pear" target="_blank" rel="nofollow noopener">google-research.github.io/vision_transfo…
English


















