CLIP ViT B 16 Laion2b S34b B88k

🚀 CLIP ViT-B/16 - LAION-2B

A model for zero-shot image classification, enabling researchers to explore arbitrary image classification.

🚀 Quick Start

This README provides detailed information about the CLIP ViT-B/16 - LAION-2B model, including its uses, training details, evaluation results, and more.

✨ Features

• Zero-shot Image Classification: Capable of classifying images without prior training on specific classes.
• Image and Text Retrieval: Can retrieve relevant images based on text queries and vice versa.
• Versatile Downstream Use: Suitable for various image tasks such as fine-tuning, linear probe classification, and image generation guiding.

📦 Installation

The document does not provide installation steps, so this section is skipped.

💻 Usage Examples

The document does not provide code examples, so this section is skipped.

📚 Documentation

🔍 Model Details

A CLIP ViT-B/16 model was trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip). Model training was done by Mehdi Cherti on the JUWELS Booster supercomputer.

🛠️ Uses

As per the original OpenAI CLIP model card, this model is intended as a research output for research communities. We hope it will enable researchers to better understand and explore zero-shot, arbitrary image classification and be used for interdisciplinary studies of the potential impact of such models.

🌟 Direct Use

Zero-shot image classification, image and text retrieval, among others.

⬇️ Downstream Use

Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.

⚠️ Out-of-Scope Use

As per the OpenAI models, any deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task-specific testing, especially given the variability of CLIP’s performance with different class taxonomies. Certain use cases in the domain of surveillance and facial recognition are always out-of-scope. Since the model has not been trained or evaluated on languages other than English, its use should be limited to English language use cases.

📈 Training Details

📊 Training Data

This model was trained with the 2 Billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/).

⚠️ Important Note

The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from the publicly available internet. Our recommendation is to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated, and the collected links may lead to strongly discomforting and disturbing content. It is possible to extract a “safe” subset by filtering out samples based on safety tags. However, we cannot entirely exclude the possibility of harmful content being present. We do not recommend using it for creating ready-to-go industrial products as the basic research about general properties and safety of such large-scale models is still in progress.

📋 Training Procedure

TODO

🧪 Evaluation

Evaluation was done with code in the LAION CLIP Benchmark suite.

📝 Testing Data, Factors & Metrics

• Testing Data: The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval.

📊 Results

The model achieves a 70.2 zero-shot top-1 accuracy on ImageNet-1k. An initial round of benchmarks have been performed on a wider range of datasets, currently viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb

🙏 Acknowledgements

We acknowledge the Gauss Centre for Supercomputing e.V. (http://gauss-centre.eu) for funding this part of work by providing computing time through the John von Neumann Institute for Computing (NIC) on the GCS Supercomputer JUWELS Booster at Jülich Supercomputing Centre (JSC).

📑 Citation

BibTeX:

LAION-5B

@inproceedings{schuhmann2022laionb,
  title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
  author={Christoph Schuhmann and
          Romain Beaumont and
          Richard Vencu and
          Cade W Gordon and
          Ross Wightman and
          Mehdi Cherti and
          Theo Coombes and
          Aarush Katta and
          Clayton Mullis and
          Mitchell Wortsman and
          Patrick Schramowski and
          Srivatsa R Kundurthy and
          Katherine Crowson and
          Ludwig Schmidt and
          Robert Kaczmarczyk and
          Jenia Jitsev},
  booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year={2022},
  url={https://openreview.net/forum?id=M3Y74vmsMcY}
}

OpenAI CLIP paper

@inproceedings{Radford2021LearningTV,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
  booktitle={ICML},
  year={2021}
}

OpenCLIP software

@software{ilharco_gabriel_2021_5143773,
  author       = {Ilharco, Gabriel and
                  Wortsman, Mitchell and
                  Wightman, Ross and
                  Gordon, Cade and
                  Carlini, Nicholas and
                  Taori, Rohan and
                  Dave, Achal and
                  Shankar, Vaishaal and
                  Namkoong, Hongseok and
                  Miller, John and
                  Hajishirzi, Hannaneh and
                  Farhadi, Ali and
                  Schmidt, Ludwig},
  title        = {OpenCLIP},
  month        = jul,
  year         = 2021,
  note         = {If you use this software, please cite it as below.},
  publisher    = {Zenodo},
  version      = {0.1},
  doi          = {10.5281/zenodo.5143773},
  url          = {https://doi.org/10.5281/zenodo.5143773}
}