Vit Small Patch16 Dinov3 Qkvb.eupe Lvd1689m

Model card for vit_small_patch16_dinov3_qkvb.eupe_lvd1689m

An EUPE Vision Transformer image feature encoder. Distilled on LVD-1689M using the Efficient Universal Perception Encoder method, from a proxy teacher distilled from multiple domain-expert foundation vision encoders.

Model Notes

• EUPE ViT checkpoints expose class, register, and patch tokens. In timm, global pooling defaults to average pooling; pass global_pool="token" or use --gp token to follow the upstream class-token pooling convention.

Model Details

• Model Type: Image Feature Encoder
• Model Stats:
  • Params (M): 21.6
  • GMACs: 6.3
  • Activations (M): 17.0
  • Image size: 256 x 256
• Original: https://github.com/facebookresearch/EUPE
• License: FAIR Noncommercial Research License
• Dataset: LVD-1689M
• Papers:
  • Efficient Universal Perception Encoder: https://arxiv.org/abs/2603.22387
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
  • PyTorch Image Models: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('vit_small_patch16_dinov3_qkvb.eupe_lvd1689m', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Feature Map Extraction

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'vit_small_patch16_dinov3_qkvb.eupe_lvd1689m',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 384, 16, 16])
    #  torch.Size([1, 384, 16, 16])
    #  torch.Size([1, 384, 16, 16])

    print(o.shape)

Image Embeddings

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'vit_small_patch16_dinov3_qkvb.eupe_lvd1689m',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 261, 384) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

Model Comparison

See the associated paper for details on the evaluation protocols.

Model	Params	IN1k-ZS	IN1k-KNN	TextVQA	SQA	Realworld	POPE	GQA	MMEp	SPair	NYUv2	ADE20k
EUPE-ViT-T	6M	50.5	66.3	42.0	69.5	50.0	82.4	61.4	1258.0	37.2	0.571	36.7
EUPE-ViT-S	20M	69.8	78.2	44.1	69.3	51.7	84.5	65.0	1304.9	46.5	0.455	46.6
EUPE-ViT-B	86M	79.7	84.1	50.4	69.7	55.5	85.9	67.3	1374.5	51.3	0.391	52.4

Citation

@misc{zhu2026eupe,
  title={Efficient Universal Perception Encoder},
  author={Zhu, Chenchen and Suri, Saksham and Jose, Cijo and Oquab, Maxime and Szafraniec, Marc and Wen, Wei and Xiong, Yunyang and Labatut, Patrick and Bojanowski, Piotr and Krishnamoorthi, Raghuraman and Chandra, Vikas},
  year={2026},
  eprint={2603.22387},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2603.22387},
}

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}