This repository contains the implementation code for paper:
Residual Learning for Long-tailed Recognition https://arxiv.org/abs/2101.10633

If you find this code or idea useful, please consider citing our work:

@article{cui2021reslt,
  title={ResLT: Residual Learning for Long-tailed Recognition},
  author={Cui, Jiequan and Liu, Shu and Tian, Zhuotao and Zhong, Zhisheng and Jia, Jiaya},
  journal={arXiv preprint arXiv:2101.10633},
  year={2021}
}

We further verifty the proposed ResLT is complementary to ensemble-based methods. Equipped with RIDEResNeXt, our model achieves better results. All experiments are conducted without knowledge distillation for fair comparison. For RIDE, we use their public code and train 180 epochs.

In this paper, we proposed a residual learning method to address long-tailed recognition, which contains a Residual Fusion Module and a Parameter Specialization Mechanism. With extensive ablation studies, we demonstrate the effectiveness of our method.

For CIFAR, due to the small data size, different experimental environment can have a big difference. To achieve the reported results, you may need to slightly tune the $\alpha$.

bash sh/CIFAR100/CIFAR100LT_imf0.01_resnet32sx1_beta0.9950.sh

For ImageNet-LT,

bash sh/X50.sh

For iNaturalist 2018,

bash sh/R50.sh

This code is partly based on the open-source implementations from offical PyTorch examples and LDAM-DRW.

If you have any questions, feel free to contact us through email ([email protected]) or Github issues. Enjoy!