Model card for naflexvit_base_patch16_radio_v3.c_radio

A C-RADIOv3 (Agglomerative Vision Foundation Model) image feature encoder by NVIDIA. C-RADIOv3 was trained by multi-teacher distillation from DFN5B CLIP ViT-H/14-378, SigLIP2-SO400M, DINOv2-g/14 (w/ registers), SAM ViT-H. This is the NaFlexViT variant. It keeps RADIO's full 128x128 (2048px) position embedding grid and matches the original RADIO position embedding resizing at any resolution or aspect ratio. It supports timm's NaFlex variable resolution / aspect ratio data pipeline for training and inference. A fixed resolution VisionTransformer variant is available as vit_base_patch16_radio_v3.

NOTE: This checkpoint is a native timm remap of NVIDIA's original nvidia/C-RADIOv3-B weights, with no additional training. Licensed by NVIDIA Corporation under the NVIDIA Open Model License, see LICENSE.pdf and NOTICE.

Model Notes

The 8 prefix tokens are one CLS (summary) token per teacher followed by registers. timm models them as a cls_token plus reg_token. The default global_pool='token' uses the first CLS token. RADIO's summary output is the concatenation of CLS tokens [0, 1, 2] (DFN CLIP, SigLIP2, DINOv2), see usage below.
Teacher adaptor heads are not included, so zero-shot text alignment from the original repository is not available.
RADIO normalizes [0, 1] inputs internally with OpenAI CLIP mean / std. The timm pretrained_cfg applies the same normalization in the data transforms.
The original bias-free patch embedding linear projection is remapped to a linear projection with a zero bias. Position embeddings are resized with bilinear interpolation without antialiasing, to a square of the larger grid dimension then cropped top-left, with align_corners=True matching the original Hub model code for this checkpoint.

Model Details

Model Type: Image Feature Encoder
Model Stats:
- Params (M): 98.3
- GMACs: 108.0
- Activations (M): 249.3
- Image size: 512 x 512
Source revision: 44653a0482cf460bb4f12595fc3cc3dfecc403d1
Original: https://github.com/NVlabs/RADIO
Original weights: https://huggingface.co/nvidia/C-RADIOv3-B
License: NVIDIA Open Model License
Training data: NV-CC-Img-Text-Dataset (per NVIDIA model card)
Teachers:
- DFN5B CLIP ViT-H/14-378
- SigLIP2-SO400M
- DINOv2-g/14 (w/ registers)
- SAM ViT-H
Papers:
- RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models: https://arxiv.org/abs/2412.07679
- FeatSharp: Your Vision Model Features, Sharper: https://arxiv.org/abs/2502.16025
- PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation: https://arxiv.org/abs/2410.01680
- AM-RADIO: Agglomerative Vision Foundation Model - Reduce All Domains Into One: https://arxiv.org/abs/2312.06709
- PyTorch Image Models: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Embeddings and Spatial Features

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

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

model = timm.create_model('hf-hub:timm/naflexvit_base_patch16_radio_v3.c_radio', pretrained=True).eval()
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
x = transforms(img).unsqueeze(0)

with torch.inference_mode():
    tokens = model.forward_features(x)  # (1, 1032, 768): prefix + patch tokens
    embedding = model.forward_head(tokens, pre_logits=True)  # (1, 768): first CLS token

# RADIO style outputs
summary = tokens[:, [0, 1, 2]].flatten(1)  # (1, 2304)
spatial = tokens[:, model.num_prefix_tokens:]  # (1, 1024, 768)

Intermediate Feature Maps

with torch.inference_mode():
    maps = model.forward_intermediates(x, indices=4, output_fmt='NCHW', intermediates_only=True)
for feature_map in maps:
    print(feature_map.shape)  # (1, 768, 32, 32)

Model Comparison

Results as reported by NVIDIA in the original C-RADIOv4 model cards. Zero-shot results use the original SigLIP2 adaptor and text encoder, which are not included here.

Benchmark	C-RADIOv3-B	C-RADIOv3-L	C-RADIOv4-SO400M	C-RADIOv3-H	C-RADIOv4-H
ImageNet Zero-Shot (Top-1)	71.30	79.95	82.01	82.65	83.09
ImageNet kNN (Top-1)	81.22	84.33	85.75	86.23	86.68
ADE20k Semantic Segmentation (mIoU)	49.79	51.87	55.14	52.75	55.20
Pascal VOC Semantic Segmentation (mIoU)	84.68	86.12	87.22	86.41	87.24

Citation

@misc{heinrich2025radiov25improvedbaselinesagglomerative,
  title={RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models},
  author={Greg Heinrich and Mike Ranzinger and Hongxu and Yin and Yao Lu and Jan Kautz and Andrew Tao and Bryan Catanzaro and Pavlo Molchanov},
  year={2024},
  eprint={2412.07679},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2412.07679},
}

@inproceedings{ranzinger2025featsharp,
  title={FeatSharp: Your Vision Model Features, Sharper},
  author={Mike Ranzinger and Greg Heinrich and Pavlo Molchanov and Bryan Catanzaro and Andrew Tao},
  booktitle={Forty-second International Conference on Machine Learning},
  year={2025},
  url={https://openreview.net/forum?id=lioemOcq3H}
}

@misc{ranzinger2024phisdistributionbalancinglabelfree,
  title={PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation},
  author={Mike Ranzinger and Jon Barker and Greg Heinrich and Pavlo Molchanov and Bryan Catanzaro and Andrew Tao},
  year={2024},
  eprint={2410.01680},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2410.01680},
}

@InProceedings{Ranzinger_2024_CVPR,
  author    = {Ranzinger, Mike and Heinrich, Greg and Kautz, Jan and Molchanov, Pavlo},
  title     = {AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month     = {June},
  year      = {2024},
  pages     = {12490-12500}
}

@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}}
}