-
CanViT: Toward Active-Vision Foundation Models
Paper • 2603.22570 • Published • 13 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • 98.1M • Updated • 1.15k • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • 95.9M • Updated • 1.55k • 1 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22
Image Feature Extraction • 98.1M • Updated • 190
CanViT
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
CanViT, the Canvas Vision Transformer, is an active-vision foundation model: it sees a scene through a sequence of glimpses and remembers it on a scene-wide canvas.
Linear segmentation probes trained on frozen CanViT canvas features for ADE20K semantic segmentation (150 classes).
-
canvit/probe-ade20k-40k-s512-c8-in21k
Image Segmentation • 160k • Updated • 36 -
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • 160k • Updated • 35 -
canvit/probe-ade20k-40k-s512-c10-in21k
Image Segmentation • 160k • Updated • 40 -
canvit/probe-ade20k-40k-s512-c12-in21k
Image Segmentation • 160k • Updated • 53
-
CanViT: Toward Active-Vision Foundation Models
Paper • 2603.22570 • Published • 13 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in21k-dv3b16-2026-02-02
Image Feature Extraction • 98.1M • Updated • 1.15k • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • 95.9M • Updated • 1.55k • 1 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22
Image Feature Extraction • 98.1M • Updated • 190
Linear segmentation probes trained on frozen CanViT canvas features for ADE20K semantic segmentation (150 classes).
-
canvit/probe-ade20k-40k-s512-c8-in21k
Image Segmentation • 160k • Updated • 36 -
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • 160k • Updated • 35 -
canvit/probe-ade20k-40k-s512-c10-in21k
Image Segmentation • 160k • Updated • 40 -
canvit/probe-ade20k-40k-s512-c12-in21k
Image Segmentation • 160k • Updated • 53
models 92
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s6
Reinforcement Learning • 5.67M • Updated • 37
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s7
Reinforcement Learning • 5.67M • Updated • 36
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s5
Reinforcement Learning • 5.67M • Updated • 37
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s4
Reinforcement Learning • 5.67M • Updated • 37
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s3
Reinforcement Learning • 5.67M • Updated • 37
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s2
Reinforcement Learning • 5.67M • Updated • 43
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s1
Reinforcement Learning • 5.67M • Updated • 43
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s0
Reinforcement Learning • 5.67M • Updated • 90
canvit/qpolicy-ade20k-c64-t5-2026-07-03
Reinforcement Learning • 5.67M • Updated • 34
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • 160k • Updated • 35
datasets 0
None public yet