Segment object using one example without training using target-guided attention with PerSAM
Segment object using one example without training using target-guided attention with PerSAM
Personalize Segment Anything Model with One Shot
arXiv paper abstract https://arxiv.org/abs/2305.03048
arXiv PDF paper https://arxiv.org/pdf/2305.03048.pdf
GitHub https://github.com/ZrrSkywalker/Personalize-SAM
Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models.
Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images.
… propose a training-free Personalization approach for SAM, termed as PerSAM.
Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or videos via three techniques: target-guided attention, target-semantic prompting, and cascaded post-refinement.
… further … present an efficient one-shot fine-tuning variant, PerSAM-F.
Freezing the entire SAM, … introduce two learnable weights for multi-scale masks, only training 2 parameters within 10 seconds for improved performance …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
