CanViT
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
CanViT (Canvas Vision Transformer) is a scalable recurrent architecture for the Active-Vision Foundation Model (AVFM) era.
See https://github.com/m2b3/CanViT-PyTorch and CanViT: Toward Active-Vision Foundation Models for more.
models 29
canvit/probe-ade20k-40k-s512-c12-in21k
Image Segmentation • Updated
canvit/probe-ade20k-40k-s512-c10-in21k
Image Segmentation • Updated
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • Updated
canvit/probe-ade20k-40k-dv3s-512px
Image Segmentation • Updated • 16
canvit/probe-ade20k-40k-dv3s-384px
Image Segmentation • Updated • 16
canvit/probe-ade20k-40k-dv3s-256px
Image Segmentation • Updated • 12
canvit/probe-ade20k-40k-dv3s-192px
Image Segmentation • Updated • 13
canvit/probe-ade20k-40k-dv3s-144px
Image Segmentation • Updated • 13
canvit/probe-ade20k-40k-dv3s-160px
Image Segmentation • Updated • 11
canvit/probe-ade20k-40k-dv3s-128px
Image Segmentation • Updated • 13
datasets 0
None public yet