-
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 • 456 • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • 95.9M • Updated • 124 • 1 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22
Image Feature Extraction • 98.1M • Updated • 29
CanViT
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
canvit/probe-ade20k-40k-dv3b-128px
Image Segmentation • 118k • Updated • 48 -
canvit/probe-ade20k-40k-dv3b-144px
Image Segmentation • 118k • Updated • 33 -
canvit/probe-ade20k-40k-dv3b-160px
Image Segmentation • 118k • Updated • 25 -
canvit/probe-ade20k-40k-dv3b-192px
Image Segmentation • 118k • Updated • 26
Learned viewing policies for a frozen CanViT. 2026-07-04 qband: 8 seeds; flagship = s2. Code: github.com/m2b3/CanViT-PyTorch-RL
-
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s0
Reinforcement Learning • 5.68M • Updated • 8 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s1
Reinforcement Learning • 5.68M • Updated • 7 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s2
Reinforcement Learning • 5.68M • Updated • 8 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s3
Reinforcement Learning • 5.68M • Updated • 14
JAX / Flax NNX checkpoints for CanViT. https://github.com/yberreby/CanViT-NNX
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 • 31 -
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • 160k • Updated • 26 -
canvit/probe-ade20k-40k-s512-c10-in21k
Image Segmentation • 160k • Updated • 25 -
canvit/probe-ade20k-40k-s512-c12-in21k
Image Segmentation • 160k • Updated • 29
Linear IN1k classification probes for DINOv3 ViT backbones @ 512x512.
-
canvit/dinov3-vits16-lvd1689m-in1k-512x512-linear-clf-probe
385k • Updated • 19 -
canvit/dinov3-vits16plus-lvd1689m-in1k-512x512-linear-clf-probe
385k • Updated • 20 -
canvit/dinov3-vitb16-lvd1689m-in1k-512x512-linear-clf-probe
769k • Updated • 73 -
canvit/dinov3-vitl16-lvd1689m-in1k-512x512-linear-clf-probe
1.03M • Updated • 34
Ablation checkpoints for the CanViT pretraining ablation study (appendix).
-
canvit/canvitb16-abl-baseline-2026-03-02
Image Feature Extraction • 98.1M • Updated • 50 -
canvit/canvitb16-abl-dcan256-2026-03-02
Image Feature Extraction • 90.4M • Updated • 43 -
canvit/canvitb16-abl-no-bptt-2026-03-06
Image Feature Extraction • 98.1M • Updated • 46 -
canvit/canvitb16-abl-no-dense-2026-03-02
Image Feature Extraction • 98.1M • Updated • 48
-
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 • 456 • 3 -
canvit/canvitb16-add-vpe-finetune-g128px-s512px-in1k-2026-04-06
Image Classification • 95.9M • Updated • 124 • 1 -
canvit/canvitb16-add-vpe-pretrain-g128px-s512px-in1k-dv3b16-2026-06-22
Image Feature Extraction • 98.1M • Updated • 29
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 • 31 -
canvit/probe-ade20k-40k-s512-c9-in21k
Image Segmentation • 160k • Updated • 26 -
canvit/probe-ade20k-40k-s512-c10-in21k
Image Segmentation • 160k • Updated • 25 -
canvit/probe-ade20k-40k-s512-c12-in21k
Image Segmentation • 160k • Updated • 29
-
canvit/probe-ade20k-40k-dv3b-128px
Image Segmentation • 118k • Updated • 48 -
canvit/probe-ade20k-40k-dv3b-144px
Image Segmentation • 118k • Updated • 33 -
canvit/probe-ade20k-40k-dv3b-160px
Image Segmentation • 118k • Updated • 25 -
canvit/probe-ade20k-40k-dv3b-192px
Image Segmentation • 118k • Updated • 26
Linear IN1k classification probes for DINOv3 ViT backbones @ 512x512.
-
canvit/dinov3-vits16-lvd1689m-in1k-512x512-linear-clf-probe
385k • Updated • 19 -
canvit/dinov3-vits16plus-lvd1689m-in1k-512x512-linear-clf-probe
385k • Updated • 20 -
canvit/dinov3-vitb16-lvd1689m-in1k-512x512-linear-clf-probe
769k • Updated • 73 -
canvit/dinov3-vitl16-lvd1689m-in1k-512x512-linear-clf-probe
1.03M • Updated • 34
Learned viewing policies for a frozen CanViT. 2026-07-04 qband: 8 seeds; flagship = s2. Code: github.com/m2b3/CanViT-PyTorch-RL
-
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s0
Reinforcement Learning • 5.68M • Updated • 8 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s1
Reinforcement Learning • 5.68M • Updated • 7 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s2
Reinforcement Learning • 5.68M • Updated • 8 -
canvit/qpolicy-ade20k-c64-t5-qband-2026-07-04-s3
Reinforcement Learning • 5.68M • Updated • 14
Ablation checkpoints for the CanViT pretraining ablation study (appendix).
-
canvit/canvitb16-abl-baseline-2026-03-02
Image Feature Extraction • 98.1M • Updated • 50 -
canvit/canvitb16-abl-dcan256-2026-03-02
Image Feature Extraction • 90.4M • Updated • 43 -
canvit/canvitb16-abl-no-bptt-2026-03-06
Image Feature Extraction • 98.1M • Updated • 46 -
canvit/canvitb16-abl-no-dense-2026-03-02
Image Feature Extraction • 98.1M • Updated • 48
JAX / Flax NNX checkpoints for CanViT. https://github.com/yberreby/CanViT-NNX