README.md

metadata

license: bsd-3-clause
datasets:
  - ILSVRC/imagenet-1k
metrics:
  - accuracy
pipeline_tag: image-classification

Model Card for rope_mixed_deit_small_patch16_LS

ImageNet-1k DeiT-iii pre-trained model with Rotary Position Embedding

Rotary Position Embedding for Vision Transformer [ECCV 2024]

• Repository: https://github.com/naver-ai/rope-vit
• Paper: https://arxiv.org/abs/2403.13298

Citation

@inproceedings{heo2024ropevit,
    title={Rotary Position Embedding for Vision Transformer},
    author={Heo, Byeongho and Park, Song and Han, Dongyoon and Yun, Sangdoo},
    year={2024},
    booktitle={European Conference on Computer Vision (ECCV)},
}