Vit So400m Patch14 Siglip Gap 224.v2 Webli

🚀 Model card for vit_so400m_patch14_siglip_gap_224.v2_webli

A SigLIP 2 ViT (image encoder only) for timm. It is equivalent to the image tower from https://huggingface.co/timm/ViT-SO400M-14-SigLIP2. The gap variant uses global average pooling and has the attention pooling head removed.

🚀 Quick Start

This model is a SigLIP 2 ViT image encoder designed for timm. It offers a way to extract image features with specific pooling mechanisms.

✨ Features

• Based on SigLIP 2 architecture for improved performance.
• Uses global average pooling (gap variant) with the attention pooling head removed.

📚 Documentation

🔍 Model Details

📄 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}
        }