https://github.com/yun-liu/HAT-Net

Vision Transformers with Hierarchical Attention
https://github.com/yun-liu/HAT-Net

Last synced: about 2 months ago
JSON representation

Vision Transformers with Hierarchical Attention

• Host: GitHub
• URL: https://github.com/yun-liu/HAT-Net
• Owner: yun-liu
• Created: 2021-06-10T06:47:18.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2024-09-15T14:26:37.000Z (3 months ago)
• Last Synced: 2024-09-15T15:43:31.904Z (3 months ago)
• Language: Python
• Homepage:
• Size: 42 KB
• Stars: 88
• Watchers: 8
• Forks: 8
• Open Issues: 5
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome_vision_transformer - code
• awesome_vision_transformer - code

README

        
## [Vision Transformers with Hierarchical Attention](https://arxiv.org/abs/2106.03180)

### This work is first titled ["Transformer in Convolutional Neural Networks"](https://arxiv.org/abs/2106.03180v2).

### Installation

This repository exactly follows the code and the training settings of [PVT](https://github.com/whai362/PVT).

### Image classification on the ImageNet-1K dataset

|     Methods     |   Size    | #Params | #FLOPs | Acc@1 |  Pretrained Models  |

|-----------------|:---------:|:-------:|:------:|:-----:|:-------------------:|

|  HAT-Net-Tiny   | 224 x 224 |  12.7M  |  2.0G  |  79.8 | [Google](https://drive.google.com/file/d/1iuhOCEMhEqJlCJKk--Qk1w6TcxP_Plgf/view?usp=sharing) / [Github](https://github.com/yun-liu/HAT-Net/releases/download/v2.0/HAT-Net_Tiny.pth) |

|  HAT-Net-Small  | 224 x 224 |  25.7M  |  4.3G  |  82.6 | [Google](https://drive.google.com/file/d/1lfVT_nCndVAPikAivigl72Ne5XKjfkCp/view?usp=sharing) / [Github](https://github.com/yun-liu/HAT-Net/releases/download/v2.0/HAT-Net_Small.pth) |

|  HAT-Net-Medium | 224 x 224 |  42.9M  |  8.3G  |  84.0 | [Google](https://drive.google.com/file/d/1fWITg1Cfm0qDaYw7xhfF8pXdbhK5ctHY/view?usp=sharing) / [Github](https://github.com/yun-liu/HAT-Net/releases/download/v2.0/HAT-Net_Medium.pth) |

|  HAT-Net-Large  | 224 x 224 |  63.1M  |  11.5G |  84.2 | [Google](https://drive.google.com/file/d/1MPNd86S_BvtPDrH_h39vjjvN12opsMki/view?usp=sharing) / [Github](https://github.com/yun-liu/HAT-Net/releases/download/v2.0/HAT-Net_Large.pth) |

### Citation

If you are using the code/models provided here in a publication, please consider citing:

    @article{liu2024vision,

      title={Vision Transformers with Hierarchical Attention},

      author={Liu, Yun and Wu, Yu-Huan and Sun, Guolei and Zhang, Le and Chhatkuli, Ajad and Van Gool, Luc},

      journal={Machine Intelligence Research},

      volume={21},

      pages={670--683},

      year={2024},

      publisher={Springer}

    }

    @article{liu2021transformer,

      title={Transformer in Convolutional Neural Networks},

      author={Liu, Yun and Sun, Guolei and Qiu, Yu and Zhang, Le and Chhatkuli, Ajad and Van Gool, Luc},

      journal={arXiv preprint arXiv:2106.03180},

      year={2021}

    }