Tinyclip ViT 8M 16 Text 3M YFCC15M

🚀 TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance

TinyCLIP is a novel cross-modal distillation method for large-scale language-image pre-trained models. It introduces two core techniques: affinity mimicking and weight inheritance. This approach unleashes the potential of small CLIP models, fully utilizing large-scale models, pre-training data, and achieving an optimal balance between speed and accuracy.

🚀 Quick Start

Use with Transformers

from PIL import Image
import requests

from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M")
processor = CLIPProcessor.from_pretrained("wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)

outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities

✨ Features

• TinyCLIP ViT-45M/32 uses only half parameters of ViT-B/32 to achieves comparable zero-shot performance.
• TinyCLIP ResNet-19M reduces the parameters by 50% while getting 2x inference speedup, and obtains 56.4% accuracy on ImageNet.

📚 Documentation

Model Zoo

Note: The configs of models with auto inheritance are generated automatically.

Official PyTorch Implementation

https://github.com/microsoft/Cream/tree/main/TinyCLIP

📄 License

• License

📚 Citation

If this repo is helpful for you, please consider to cite it. :mega: Thank you! :)

@InProceedings{tinyclip,
    title     = {TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance},
    author    = {Wu, Kan and Peng, Houwen and Zhou, Zhenghong and Xiao, Bin and Liu, Mengchen and Yuan, Lu and Xuan, Hong and Valenzuela, Michael and Chen, Xi (Stephen) and Wang, Xinggang and Chao, Hongyang and Hu, Han},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {21970-21980}
}

💡 Acknowledge

Our code is based on CLIP, OpenCLIP, CoFi and PyTorch. Thank contributors for their awesome contribution!