CanViT pretraining ablation: D_can = 256, asymmetric

One of the paper's pretraining ablations: a short pretraining run that changes one design choice of CanViT-B. Reproduce it with python -m canvit_pytorch.pretrain --ablation dcan256.

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.

Paper (NeurIPS 2026) · Code · Project page · All checkpoints

Usage

uv add "canvit-pytorch>=0.2"
import torch
from PIL import Image
from canvit_pytorch import CanViTForPretraining
from canvit_pytorch.episode import run_episode
from canvit_pytorch.policies import make_policy
from canvit_pytorch.preprocess import preprocess

model = CanViTForPretraining.from_pretrained("canvit/canvitb16-abl-dcan256-2026-03-02").eval()
scene = preprocess(512)(Image.open("scene.jpg").convert("RGB")).unsqueeze(0)  # [1, 3, 512, 512]

# Five glimpses of 128 px, coarse to fine: the full scene, then quadrants.
policy = make_policy("coarse_to_fine", batch_size=1, device=scene.device, num_glimpses=5, canvas_grid_size=32)
with torch.inference_mode():
    steps = run_episode(
        canvit=model.canvit, images=scene, policy=policy, num_glimpses=5, glimpse_size_px=128,
        initial_state=model.init_state(batch_size=1, canvas_grid_size=32),
    )
    canvas = steps[-1].state.canvas
    features = model.canvit.canvas_patch_grid(canvas)  # [1, 32, 32, canvas_dim]: the scene-wide canvas
    teacher_patches = model.predict_teacher_patches(canvas)  # the teacher's features of the whole scene, standardized

Details

Pretraining data ImageNet-21k
Teacher facebook/dinov3-vitb16-pretrain-lvd1689m
Scenes 512 px
Glimpses 128 px
Canvas during pretraining 32 × 32 (any size at inference)
Training steps 214,656

License

MIT. CanViT is pretrained by distillation from DINOv3, which is released under the DINOv3 License.

Citation

@inproceedings{berreby2026canvit,
  title={CanViT: Toward Active-Vision Foundation Models},
  author={Berreby, Yoha{\"i}-Eliel and Du, Sabrina and Durand, Audrey and Krishna, B. Suresh},
  booktitle={Advances in Neural Information Processing Systems},
  year={2026},
  eprint={2603.22570},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2603.22570}
}

canvit-pytorch 0.1

This repository's files for canvit-pytorch 0.1 remain at revision canvit-pytorch-0.1: with canvit-pytorch<0.2, pass revision="canvit-pytorch-0.1" to from_pretrained.

Downloads last month
4,866
Safetensors
Model size
90.4M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for canvit/canvitb16-abl-dcan256-2026-03-02

Finetunes
1 model

Collection including canvit/canvitb16-abl-dcan256-2026-03-02

Paper for canvit/canvitb16-abl-dcan256-2026-03-02