BEiT

Category: ViT · Code: timm/models/beit.py · Architectures: 7 · Pretrained weights: 13 (9 with ImageNet-1k results)

BEiT and BEiT-v2 Vision Transformers, pretrained with masked image modeling. BEiT predicts the discrete visual tokens of masked patches, BEiT-v2 uses a vector-quantized visual tokenizer for the targets. The weights here are fine-tuned classification weights.

Papers

• BEiT: BERT Pre-Training of Image Transformers
• BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers

Usage

See the Quickstart for loading pretrained weights, image preprocessing and fine-tuning, and Feature Extraction for using the models as backbones.

>>> import timm
>>> model = timm.create_model('beit_base_patch16_224.in22k_ft_in22k_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)

Model API support

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input size). Checked by running each feature on a randomly initialized model (Beit with beit_base_patch16_224 at 224), other architectures of the same class are expected to behave the same. See the Model API page for details.

Architectures

GMACs and parameter counts are for the default input size and classifier of each architecture, from the benchmark results.

Pretrained weights

Top-1 is ImageNet-1k validation accuracy from results-imagenet.csv at the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the size of the pretrained classifier, none for weights without one.

Citation

@inproceedings{beit,
title={{BEiT}: {BERT} Pre-Training of Image Transformers},
author={Hangbo Bao and Li Dong and Songhao Piao and Furu Wei},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=p-BhZSz59o4}
}

@article{beitv2,
title={{BEiT v2}: Masked Image Modeling with Vector-Quantized Visual Tokenizers},
author={Zhiliang Peng and Li Dong and Hangbo Bao and Qixiang Ye and Furu Wei},
year={2022},
eprint={2208.06366},
archivePrefix={arXiv},
primaryClass={cs.CV}
}