Models / CIDAS / CLIPSeg (RD64)

CLIPSeg (RD64)

JSON →
vision

A CLIP-based segmentation model for referring image segmentation with RD64 decoder.

imagetextvision
homepage ↗
Specs
Context & limits
—
context window
—
max output
Lifecycle
Dates
released2022-03-01
Resources
homepagehttps://huggingface.co/CIDAS/clipseg-rd64 ↗