CrossViT

Category: ViT · Code: timm/models/crossvit.py · Architectures: 11 · Pretrained weights: 11 (11 with ImageNet-1k results)

CrossViT processes small and large image patches in two Transformer branches and fuses them with cross-attention through the class tokens. Model names in timm give the actual input resolution (240 / 408 instead of the original 224 / 384).

Papers

• CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

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('crossvit_small_240.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 (CrossVit with crossvit_tiny_240 at 240), 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{
    chen2021crossvit,
    title={{CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification}},
    author={Chun-Fu (Richard) Chen and Quanfu Fan and Rameswar Panda},
    booktitle={International Conference on Computer Vision (ICCV)},
    year={2021}
}