Personalized Segmentation
4 papers with code • 1 benchmarks • 1 datasets
Given a one-shot image with a reference mask, the models are required to segment the indicated target object in any other images.
Most implemented papers
Visual Prompting via Image Inpainting
How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification?
Images Speak in Images: A Generalist Painter for In-Context Visual Learning
In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images.
SegGPT: Segmenting Everything In Context
We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images.
Personalize Segment Anything Model with One Shot
Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models.