Segment objects at many granularities by generating masks at multiple levels with Semantic-SAM
Segment objects at many granularities by generating masks at multiple levels with Semantic-SAM
Semantic-SAM: Segment and Recognize Anything at Any Granularity
arXiv paper abstract https://arxiv.org/abs/2307.04767
arXiv PDF paper https://arxiv.org/pdf/2307.04767.pdf
... introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.
... model offers two key advantages: semantic-awareness and granularity-abundance.
To achieve semantic-awareness ... consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts.
This allows ... model to capture rich semantic information.
For the multi-granularity capability ... propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels that correspond to multiple ground-truth masks.
... demonstrate that ... model successfully achieves semantic-awareness and granularity-abundance ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments