ViTamin-L2-336px

Model card for ViTamin-L2-336px

Official huggingface models of ViTamin, from the following CVPR 2024 paper:

ViTamin: Design Scalable Vision Models in the Vision-language Era.
✨  Jieneng Chen, Qihang Yu, Xiaohui Shen, Alan Yuille and Liang-Chieh Chen
🏠  Johns Hopkins University, Bytedance

Load from HuggingFace with transformers.AutoModel:

import torch
import open_clip
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor
device = "cuda" if torch.cuda.is_available() else "cpu"

model = AutoModel.from_pretrained(
    'jienengchen/ViTamin-L2-336px',
    trust_remote_code=True).to(device).eval()

image = Image.open('./image.png').convert('RGB')
image_processor = CLIPImageProcessor.from_pretrained('jienengchen/ViTamin-L2-336px')

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()

tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K')
text = tokenizer(["a photo of vitamin", "a dog", "a cat"]).to(device)

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features, text_features, logit_scale = model(pixel_values, text)
    text_probs = (100.0 * image_features @ text_features.to(torch.float).T).softmax(dim=-1)

print("Label probs:", text_probs)

Main Results with CLIP Pre-training on DataComp-1B

Main Results on Downstream tasks

Open-Vocab Detection

Open-Vocab Segmentation

Note: Panoptic dataset (ADE, CityScapes, MV) are with the metric of PQ. Semantic dataset (A-150, A-847, PC-459, PC-59, PAS-21) are with the metric of mIoU.

Large Multi-modal Models

Citing ViTamin

@inproceedings{chen2024vitamin,
  title={ViTamin: Design Scalable Vision Models in the Vision-language Era},
  author={Chen, Jieneng and Yu, Qihang and Shen, Xiaohui and Yuille, ALan and Chen, Liang-Chieh},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2024}
}