Home

Awesome

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Zhengzhuo Xu, Zenghao Chai, Chun Yuan


This is the PyTorch implementation of our paper in NeurIPS 2021.

Environment settings

Training

To train the model, please select a config file path or customize by yourself. For example:

python train.py config/cifar10_100.py

The result will be saved in ./result.

Inferance model

DatasetlogModel
CIFAR-10-LT-50linklink
CIFAR-10-LT-100linklink
CIFAR-10-LT-200linklink
CIFAR-100-LT-50linklink
CIFAR-100-LT-100linklink
CIFAR-100-LT-200linklink

Note

Reference

Welcome to cite:

@inproceedings{PriorLT,
    title={Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective},
    author={Xu, Zhengzhuo and Chai, Zenghao and Yuan, Chun},
    booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
    year={2021}
}

Acknowledgement

We adopt the code from the following repos. We thank them for providing their awesome code.