Skip to content

Latest commit

 

History

History
54 lines (48 loc) · 1.66 KB

README.md

File metadata and controls

54 lines (48 loc) · 1.66 KB

Paper

Improving Segment Anything on the Fly: Auxiliary Online Learning and Adaptive Fusion for Medical Image Segmentation

Datasets

download the datasets and make them with this format

.
├── TestDatasets
│   ├── BUSI
│   │   ├── benign
│   │   └── malignant
│   ├── fluidchallenge
│   │   ├── cirrus
│   │   ├── spectralis
│   │   └── topcon
│   ├── Polyp
│   │   ├── CVC-300
│   │   ├── CVC-ClinicDB
│   │   ├── CVC-ColonDB
│   │   ├── ETIS-LaribPolypDB
│   │   └── Kvasir
│   └── GlaS
│       ├── benign
│       ├── Grade.csv
│       └── malignant

Checkpoints

download the checkpoints ,create a directory named checkpoints under the root directory, put them into the directory

MedSAM checkpoints
SAM checkpoints

Getting Started

python main.py

License

The code is licensed under the MIT license.

Citing AuxOL

If you use AuxOL in your research, please use the following BibTeX entry.

@article{huang2024improving,
  title={On-the-Fly Improving Segment Anything for Medical Image Segmentation using Auxiliary Online Learning},
  author={Huang, Tianyu and Zhou, Tao and Xie, Weidi and Wang, Shuo and Dou, Qi and Zhang, Yizhe},
  journal={arXiv preprint arXiv:2406.00956},
  year={2024}
}