Below is background knowledge on the models used in our experiments.
| Title | Intro | Description | Links |
|---|---|---|---|
| Segment-Anything |  |
A strong foundation model aims to segment everything in an image, which needs prompts (as boxes/points/text) to generate masks | [Github] [Page] [Demo] |
| Grounding DINO |  |
A strong zero-shot detector which is capable of to generate high quality boxes and labels with free-form text. | [Github] [Demo] |
Simply run:
pip install -r requirements.txt
cd models && python3 install.py
If using O2, first run:
module load python/3.10.11 gcc/9.2.0 cuda/11.7