A simple image segmentation framework via in-context examples

Y Liu, C **g, H Li, M Zhu, H Chen, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, there have been explorations of generalist segmentation models that can
effectively tackle a variety of image segmentation tasks within a unified in-context learning …

There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks

M Espinosa, C Yang, L Ericsson, S McDonagh… - arxiv preprint arxiv …, 2024 - arxiv.org
The Segment Anything Model (SAM) was originally designed for label-agnostic mask
generation. Does this model also possess inherent semantic understanding, of value to …