Vit Base Patch16 Siglip Gap 224.v2 Webli

🚀 Model card for vit_base_patch16_siglip_gap_224.v2_webli

A SigLIP 2 ViT (image encoder only) for timm, equivalent to the image tower from https://huggingface.co/timm/ViT-B-16-SigLIP2. The gap variant uses global average pooling and removes the attention pooling head.

🚀 Quick Start

This is a SigLIP 2 ViT model designed for timm, focusing solely on image encoding. It's equivalent to the image tower from the specified Hugging Face model. The gap variant simplifies the model by using global average pooling and removing the attention pooling head.

📚 Documentation

Model Details

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

@article{tschannen2025siglip,
          title={SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features},
          author={Tschannen, Michael and Gritsenko, Alexey and Wang, Xiao and Naeem, Muhammad Ferjad and Alabdulmohsin, Ibrahim and Parthasarathy, Nikhil and Evans, Talfan and Beyer, Lucas and Xia, Ye and Mustafa, Basil and H'enaff, Olivier and Harmsen, Jeremiah and Steiner, Andreas and Zhai, Xiaohua},
          year={2025},
          journal={arXiv preprint arXiv:2502.14786}
        }
        

@inproceedings{zhai2023sigmoid,
          title={Sigmoid loss for language image pre-training},
          author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
          booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
          pages={11975--11986},
          year={2023}
        }