WaterMask

This repo is the official implementation of "WaterMask: Instance Segmentation for Underwater Imagery". By Shijie Lian, Hua Li, Runmin Cong, Suqi Li, Wei Zhang, Sam Kwong, and has been accepted by ICCV2023! 🎉🎉🎉

🚀 Highlights:

• UIIS dataset: We construct the first general Underwater Image Instance Segmentation (UIIS) dataset containing 4,628 images for 7 categories with pixel-level annotations for underwater instance segmentation task.

  

• SOTA performance: We propose the first underwater instance segmentation model, WaterMask, as far as we know, which achieves good performance in qualitative and quantitative comparisons with natural image instance segmentation SOTA methods.

  

Requirements

• Python 3.6+
• Pytorch 1.3+
• mmcv-full>=1.3.17, <1.6.0 (we use mmcv 1.5.3 and mmdetection 2.25.1 in code)

and you need use pip install -v -e . to install mmdetection.

Datasets

data
  ├── UDW
  |   ├── annotations
  │   │   │   ├── train.json
  │   │   │   ├── val.json
  │   ├── train
  │   │   ├── L_1.jpg
  │   │   ├── ......
  │   ├── val

you can get our UIIS dataset in Baidu Disk (pwd:fiuk) or Google Drive

Main Results

We provide some results on UIIS dataset with pretrained models. These model are trained on an NVIDIA A5000 GPU. Note that all models and logs are available at Baidu Netdisk and google drive link is coming soon too!.

model	Schedule	mAP	AP50	AP75	config	download
WaterMask R101-FPN	1x	25.6	41.7	27.9	config	log / pth
WaterMask R50-FPN	3x	26.4	43.6	28.8	config	log / pth
WaterMask R101-FPN	3x	27.2	43.7	29.3	config	log / pth
Cascade WaterMask R101-FPN	3x	27.1	42.9	30.4	config	log / pth

Training

python tools/train.py configs/_our_/water_r50_fpn_1x.py --work-dir you_dir_to_save_logs_and_models

or

bash tools/dist_train.sh configs/_our_/water_r50_fpn_1x.py NUM_GPUS --work-dir you_dir_to_save_logs_and_models

Test

python tools/test.py configs/_our_/water_r50_fpn_1x.py model_checkpoint_path --eval segm

or

bash tools/dist_test.sh configs/_our_/water_r50_fpn_1x.py model_checkpoint_path NUM_GPUS --eval segm

Citation

If you find our repo useful for your research, please cite us:

@InProceedings{Lian_2023_ICCV,
    author    = {Lian, Shijie and Li, Hua and Cong, Runmin and Li, Suqi and Zhang, Wei and Kwong, Sam},
    title     = {WaterMask: Instance Segmentation for Underwater Imagery},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {1305-1315}
}

License

This project is released under the Apache 2.0 license.

Acknowledgement

This software repository is implemented based on the MMDetection framework. Thanks to them for their excellent work.