MobileSAMv2: Faster Segment Anything to Everything

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: segment anything (SegAny), which utilizes a certain point to predict the mask for a single object of interest, and segment everything (SegEvery), which predicts the masks for all objects on the image.

Data and Resources

Cite this as

Chaoning Zhang, Dongshen Han, Sheng Zheng, Jinwoo Choi, Tae-Ho Kim, Choong Seon Hong (2024). Dataset: MobileSAMv2: Faster Segment Anything to Everything. https://doi.org/10.57702/w0fq0hhn

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2312.09579
Author Chaoning Zhang
More Authors
Dongshen Han
Sheng Zheng
Jinwoo Choi
Tae-Ho Kim
Choong Seon Hong
Homepage https://github.com/ChaoningZhang/MobileSAM