Personalize-SAM: A Training-Free Approach for Segmenting Specific Visual Concepts
Personalize-SAM is a training-free Personalization approach for Segment Anything Model (SAM). Given only a single image with a reference mask, PerSAM can segment specific visual concepts, e.g., your pet dog, within other images or videos without any training.
Personalize-SAM is based on the SAM model, which was developed by Facebook AI Research. SAM is a powerful model for segmenting arbitrary objects in images and videos. However, SAM requires a large amount of training data, which can be time-consuming and expensive to collect.
Personalize-SAM addresses this problem by using a training-free personalization approach. Given only a single image with a reference mask, PerSAM can learn to segment the same object in other images or videos. This makes it possible to use SAM to segment objects that are not present in the training data.
Personalize-SAM has been shown to be effective on a variety of tasks, including object segmentation, person re-identification, and image editing. It is a powerful tool that can be used to improve the performance of existing computer vision models.
- Clone the repository:
git clone https://github.com/ZrrSkywalker/Personalize-SAM.git
pip install -r requirements.txt
python demo.pyView on GitHub Read the paper