PRIS-CV / Top-Down-Spatial-Attention-Loss

Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features

Top-Down-Spatial-Attention-Loss

Code release for Top-Down-Spatial-Attention-Loss arXiv

Changelog

• 2021/01/24 update the code

Dataset

CUB-200-2011

Requirements

• python 3.6
• PyTorch 1.2.0
• torchvision

Training

• Download datasets
• Train: python Birds_TDSA_Loss.py
• Description : PyTorch CUB-200-2011 Training with VGG16 (TRAINED FROM SCRATCH).

Citation

If you find this paper useful in your research, please consider citing:

@article{chang2021TOP,
  title={Fine-Grained Visual Classification via Simultaneously Learning of
  Multi-regional Multi-grained Features},
  author={Chang, Dongliang and Zheng, Yixiao and Ma, Zhanyu and Du, Ruoyi and Liang, Kongming},
  journal={arXiv preprint arXiv:2102.00367},
  year={2021}
}

Contact

Thanks for your attention! If you have any suggestion or question, you can leave a message here or contact us directly:

• [e-mail]
• [e-mail]