Official PyTorch Implementation
Sen Pei, Jiaxi Sun
Institute of Automation, Chinese Academy of Sciences
- PACS: photo, art painting, cartoon, sketch
- VLCS: Pascal VOC, LabelMe, Caltech, SUN09
- OfficeHome: Artistic, Clipart, Product, Real World
- Digits-DG: MNIST, MNIST-M, SVHN, SYN
- NICO: 19 classes belonging to 65 domains
- download here: Baidu Disk (ql17)
- RandomResizedCrop
- RandomHorizontalFlip
- ColorJitter
- Normalize
- backbone: ResNet-18
- distance-based cross entropy
- ImageNet Pre-trained models
python -m torch.distributed.launch --nproc_per_node=8 pacs_train.py --n_gpus=8
python -m torch.distributed.launch --nproc_per_node=8 vlcs_train.py --n_gpus=8
python -m torch.distributed.launch --nproc_per_node=8 nico_train.py --n_gpus=8
python -m torch.distributed.launch --nproc_per_node=8 digits_train.py --n_gpus=8
python -m torch.distributed.launch --nproc_per_node=8 officehome_train.py --n_gpus=8
Methods | Art Painting | Cartoon | Photo | Sketch | Average |
---|---|---|---|---|---|
MMD-AAE | 75.20 | 72.70 | 96.00 | 64.20 | 77.03 |
CCSA | 80.50 | 76.90 | 93.60 | 66.80 | 79.45 |
ResNet-18 | 77.00 | 75.90 | 96.00 | 69.20 | 79.53 |
StableNet | 80.16 | 74.15 | 94.24 | 70.10 | 79.66 |
JiGen | 79.40 | 75.30 | 96.00 | 71.60 | 80.50 |
CrossCrad | 79.80 | 76.80 | 96.00 | 70.20 | 80.70 |
DANN | 80.20 | 77.60 | 95.40 | 70.00 | 80.80 |
Epi-FCR | 82.10 | 77.00 | 93.90 | 73.00 | 81.50 |
MetaReg | 83.70 | 77.20 | 95.50 | 70.30 | 81.70 |
GCPL | 82.64 | 75.02 | 96.40 | 73.36 | 81.86 |
EISNet | 81.89 | 76.44 | 95.93 | 74.33 | 82.15 |
L2A-OT | 83.30 | 78.20 | 96.20 | 73.60 | 82.83 |
MixStyle | 84.10 | 78.80 | 96.10 | 75.90 | 83.70 |
PoER (Ours) | 85.30 | 77.69 | 96.42 | 77.30 | 84.18 |
- Deep Residual Learning for Image Recognition (CVPR, 2016)
- Deeper, Broader and Artier Domain Generalization (ICCV, 2017)
- Robust classification with convolutional prototype learning (CVPR, 2018)
- Domain Generalization via Entropy Regularization (NeurIPS, 2020)
@misc{pei2022domain,
title={Domain Decorrelation with Potential Energy Ranking},
author={Sen Pei and Jiaxi Sun and Richard Yida Xu and and Shiming Xiang and Gaofeng Meng},
year={2022},
eprint={2207.12194},
archivePrefix={arXiv},
primaryClass={cs.CV}
}