Home

Awesome

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition [Official, ICCV 2023, Paper] šŸ”„

Qihao Zhao<sup>1,2</sup>, Chen Jiang<sup>1</sup>, Wei Hu<sup>1</sup>, Fan Zhang<sup>1</sup>, Jun Liu<sup>2</sup>

1 Beijing University of Chemical Technology

2 Singapore University of Technology and Design

MDCS

0.Citation

If you find our work inspiring or use our codebase in your research, please consider giving a star ā­ and a citation.

@InProceedings{Zhao_2023_ICCV,
    author    = {Zhao, Qihao and Jiang, Chen and Hu, Wei and Zhang, Fan and Liu, Jun},
    title     = {MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {11597-11608}
}

1.training

(1) CIFAR100-LT

Training

python train.py -c configs/config_cifar100_ir100_mdcs.json

Evaluate

python test.py -r checkpoint_path

(2) ImageNet-LT

Training

python train.py -c configs/config_imagenet_lt_resnext50_mdcs_e400.json

Evaluate

python test.py -r checkpoint_path

(3) Places-LT

Training

python train_places.py -c configs/config_places_lt_resnet152_mdcs.json

Evaluate

python test_places.py -r checkpoint_path

(4) iNaturalist 2018

Training

python train.py -c configs/config_iNaturalist_resnet50_mdcs.json

Evaluate

python test.py -r checkpoint_path

2. Requirements

pip install -r requirements.txt

3. Datasets

(1) Four bechmark datasets

data
ā”œā”€ā”€ ImageNet_LT
ā”‚Ā Ā  ā”œā”€ā”€ test
ā”‚Ā Ā  ā”œā”€ā”€ train
ā”‚Ā Ā  ā””ā”€ā”€ val
ā”œā”€ā”€ CIFAR100
ā”‚Ā Ā  ā””ā”€ā”€ cifar-100-python
ā”œā”€ā”€ Place365
ā”‚Ā Ā  ā”œā”€ā”€ data_256
ā”‚Ā Ā  ā”œā”€ā”€ test_256
ā”‚Ā Ā  ā””ā”€ā”€ val_256
ā””ā”€ā”€ iNaturalist 
 Ā Ā  ā”œā”€ā”€ test2018
    ā””ā”€ā”€ train_val2018

(2) Txt files

data_txt
ā”œā”€ā”€ ImageNet_LT
ā”‚Ā Ā  ā”œā”€ā”€ ImageNet_LT_test.txt
ā”‚Ā Ā  ā”œā”€ā”€ ImageNet_LT_train.txt
ā”‚Ā Ā  ā””ā”€ā”€ ImageNet_LT_val.txt
ā”œā”€ā”€ Places_LT_v2
ā”‚Ā Ā  ā”œā”€ā”€ Places_LT_test.txt
ā”‚Ā Ā  ā”œā”€ā”€ Places_LT_train.txt
ā”‚Ā Ā  ā””ā”€ā”€ Places_LT_val.txt
ā””ā”€ā”€ iNaturalist18
    ā”œā”€ā”€ iNaturalist18_train.txt
    ā”œā”€ā”€ iNaturalist18_uniform.txt
    ā””ā”€ā”€ iNaturalist18_val.txt 

4. Pretrained models

5. Acknowledgements

The mutli-expert framework is based on SADE and RIDE. Strong augmentations are based on NCL and PaCo.