Skip to content

Latest commit

 

History

History

mcibi

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 

README.md

Introduction

Official Repo

Code Snippet

MCIBI (ICCV'2021) 
@inproceedings{jin2021mining,
    title={Mining Contextual Information Beyond Image for Semantic Segmentation},
    author={Jin, Zhenchao and Gong, Tao and Yu, Dongdong and Chu, Qi and Wang, Jian and Wang, Changhu and Shao, Jie},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={7231--7241},
    year={2021}
}

Performance

COCOStuff-10k

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU/mIoU (ms+flip) Download
DeepLabV3 ImageNet-1k-224x224 R-50-D8 512x512 LR/POLICY/BS/EPOCH: 0.001/poly/16/110 train/test 38.84%/39.78% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 R-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.001/poly/16/110 train/test 39.84%/41.52% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.001/poly/32/150 train/test 41.18%/42.38% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 HRNetV2p-W48 512x512 LR/POLICY/BS/EPOCH: 0.001/poly/16/110 train/test 39.77%/41.48% cfg | model | log
DeepLabV3 ImageNet-22k-384x384 ViT-Large 512x512 LR/POLICY/BS/EPOCH: 0.001/poly/16/110 train/test 44.27%/45.50% cfg | model | log

ADE20k

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU/mIoU (ms+flip) Download
DeepLabV3 ImageNet-1k-224x224 R-50-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 44.39%/45.97% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 R-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 45.66%/47.27% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x512 LR/POLICY/BS/EPOCH: 0.004/poly/16/180 train/val 46.63%/47.39% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 HRNetV2p-W48 512x512 LR/POLICY/BS/EPOCH: 0.004/poly/16/180 train/val 45.79%/47.46% cfg | model | log
DeepLabV3 ImageNet-22k-384x384 ViT-Large 512x512 LR/POLICY/BS/EPOCH: 0.01/poly/16/130 train/val 49.73%/50.99% cfg | model | log

CityScapes

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU (ms+flip) Download
DeepLabV3 ImageNet-1k-224x224 R-50-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/16/440 trainval/test 79.97% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 R-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/16/440 trainval/test 82.10% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/16/500 trainval/test 81.51% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 HRNetV2p-W48 512x1024 LR/POLICY/BS/EPOCH: 0.01/poly/16/500 trainval/test 82.54% cfg | model | log

LIP

Segmentor Pretrain Backbone Crop Size Schedule Train/Eval Set mIoU/mIoU (flip) Download
DeepLabV3 ImageNet-1k-224x224 R-50-D8 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 53.73%/54.08% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 R-101-D8 473x473 LR/POLICY/BS/EPOCH: 0.01/poly/32/150 train/val 55.02%/55.42% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 S-101-D8 473x473 LR/POLICY/BS/EPOCH: 0.007/poly/40/150 train/val 56.21%/56.34% cfg | model | log
DeepLabV3 ImageNet-1k-224x224 HRNetV2p-W48 473x473 LR/POLICY/BS/EPOCH: 0.007/poly/40/150 train/val 56.40%/56.99% cfg | model | log

More

You can also download the model weights from following sources:

Due to differences in the testing environment (such as GPU, PyTorch, and CUDA versions), the model's performance may fluctuate by approximately 0.1%.