/Mutual-Channel-Loss

Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)

Primary LanguagePythonMIT LicenseMIT

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020) DOI

Dataset

CUB-200-2011

Requirements

  • python 3.6
  • PyTorch 1.2.0
  • torchvision

Training

  • Download datasets
  • Train: python CUB-200-2011.py, the alpha is the hyper-parameters of the MC-Loss
  • Description : PyTorch CUB-200-2011 Training with VGG16 (TRAINED FROM SCRATCH).

Citation

please cite:

@ARTICLE{chang2020mutualchannel,
author={D. {Chang} and Y. {Ding} and J. {Xie} and A. K. {Bhunia} and X. {Li} and Z. {Ma} and M. {Wu} and J. {Guo} and Y. {Song}},
journal={IEEE Transactions on Image Processing},
title={The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification},
year={2020},
pages={1-1},
keywords={Fine-grained image classification;deep learning;loss function;mutual channel},
doi={10.1109/TIP.2020.2973812},
ISSN={1941-0042}
}

Contact