Home

Awesome

Influence-balanced Loss for Imbalanced Visual Classification (ICCV, 2021)

This is the official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch. The code heavily relies on LDAM-DRW.

Paper | Bibtex | Video | Slides

Requirements

All codes are written by Python 3.7, and 'requirements.txt' contains required Python packages. To install requirements:

pip install -r requirements.txt

Dataset

Create 'data/' directory and download original data in the directory to make imbalanced versions.

Training

We provide several training examples:

CIFAR

python cifar_train.py --dataset cifar100 --loss_type CE --train_rule None --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --gpu 0
python cifar_train.py --dataset cifar100 --loss_type IB --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0

python cifar_train.py --dataset cifar100 --loss_type IB --train_rule CBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0

python cifar_train.py --dataset cifar100 --loss_type IBFocal --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 200 --num_classes 100 --start_ib_epoch 100 --gpu 0

Tiny ImageNet

python tinyimage_train.py --dataset tinyimagenet -a resnet18 --loss_type CE --train_rule None --imb_type exp --imb_factor 0.01 --epochs 100 --lr 0.1  --num_classes 200

python tinyimage_train.py --dataset tinyimagenet -a resnet18 --loss_type IB --train_rule IBReweight --imb_type exp --imb_factor 0.01 --epochs 100 --lr 0.1  --num_classes 200 --start_ib_epoch 50

Citation

If you find our paper and repo useful, please cite our paper

@InProceedings{Park_2021_ICCV,
    author    = {Park, Seulki and Lim, Jongin and Jeon, Younghan and Choi, Jin Young},
    title     = {Influence-Balanced Loss for Imbalanced Visual Classification},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {735-744}
}