Model card for convnext_small.eupe_lvd1689m

An EUPE ConvNeXt 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 Details

• Model Type: Image Feature Encoder
• Model Stats:
  • Params (M): 49.5
  • GMACs: 11.4
  • Activations (M): 28.2
  • 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
  • A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
  • 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('convnext_small.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(
    'convnext_small.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, 96, 64, 64])
    #  torch.Size([1, 192, 32, 32])
    #  torch.Size([1, 384, 16, 16])
    #  torch.Size([1, 768, 8, 8])

    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(
    'convnext_small.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, 768, 8, 8) 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	TextVQA	SQA	Realworld	POPE	GQA	MMEp	SPair	NYUv2	ADE20k
EUPE-ConvNeXt-T	29M	43.7	68.8	47.9	83.4	63.0	1278.1	41.3	0.430	43.5
EUPE-ConvNeXt-S	50M	45.0	68.9	50.5	84.0	64.7	1284.2	40.1	0.388	46.8
EUPE-ConvNeXt-B	89M	46.4	70.1	53.3	84.7	65.8	1348.9	37.7	0.365	48.9

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{liu2022convnet,
  author  = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
  title   = {A ConvNet for the 2020s},
  journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year    = {2022},
}

@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}}
}