This is a PyTorch implementation of the paper"Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization (MMAL-Net)"(Fan Zhang, Meng Li, Guisheng Zhai, Yizhao Liu), and the paper has been accepted by the 27th International Conference on Multimedia Modeling (MMM2021). Welcome to discuss with us in issues!
- Python 3.7
- pytorch 1.3.1
- numpy 1.17.3
- scikit-image 0.16.2
- Tensorboard 1.15.0
- TensorboardX 2.0
- tqdm 4.41.1
- imageio 2.6.1
- pillow 6.1.0
Download theCUB-200-2011datasets and copy the contents of the extractedimagesfolder intodatasets/CUB 200-2011/images.
Download theFGVC-Aircraftdatasets and copy the contents of the extracteddata/imagesfolder intodatasets/FGVC_Aircraft/data/images)
You can also try other fine-grained datasets.
If you want to train the MMAL-Net, please download the pretrained model ofResNet-50and move it tomodels/pretrainedbefore runPython train.py.You may need to change the configurations inconfig.pyif your GPU memory is not enough. The parameterN_listisN1, N2, N3in the original paper and you can adjust them according to GPU memory. During training, the log file and checkpoint file will be saved inmodel_pathdirectory.
If you want to test the MMAL-Net, just runPython test.py.You need to specify themodel_pathintest.pyto choose the checkpoint model for testing.
We also provide the checkpoint model trained by ourselves, you can download if fromGoogle DriveforCUB-200-2011or download fromhereforFGVC-Aircraft.If you test on our provided model, you will get 89.6% and 94.7% test accuracy, respectively.
If you are interested in our work and want to cite it, please acknowledge the following paper:
@misc{zhang2020threebranch,
title={Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization},
author={Fan Zhang and Meng Li and Guisheng Zhai and Yizhao Liu},
year={2020},
eprint={2003.09150},
archivePrefix={arXiv},
primaryClass={cs.CV}
}