This repository is the official implementation of "Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation".
If you found this project useful, please give us a star ⭐️ or cite us in your paper, this is the greatest support and encouragement for us.
🚩 News (2025.05) We propose a large-scale underwater instance segmentation dataset, UIIS10K, which includes 10,048 images with pixel-level annotations for 10 categories. As far as we know, this is the largest underwater instance segmentation dataset available and can be used as a benchmark for evaluating underwater segmentation methods.
The dataset follows the COCO format and is organized as follows:
data
├── UIIS10K
| ├── annotations
│ │ ├── multiclass_train.json
│ │ ├── multiclass_test.json
│ ├── img
│ │ ├── train_00001.jpg
│ │ ├── ...
│ │ ├── test_00001.jpg
│ │ ├── ...
you can get our UIIS10K dataset in Hugging Face, Baidu Disk (pwd:UIIS), or Google Drive.
Code is coming soon
If you find our repo useful for your research, please cite us:
@InProceedings{UIIS_Dataset_2023,
author = {Shijie Lian, Hua Li, Runmin Cong, Suqi Li, Wei Zhang, Sam Kwong},
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}
}
@article{UIIS10K_Dataset_2025,
author = {Hua Li, Shijie Lian, Zhiyuan Li, Runmin Cong, Chongyi Li, Laurence T. Yang, Weidong Zhang, Sam Kwong},
title = {Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation},
year = {2025},
journal = {arXiv preprint arXiv:2505.15581},
}