Segment image with one example using model correspondence between example and target with SEGIC
Segment image with one example using model correspondence between example and target with SEGIC
SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
arXiv paper abstract https://arxiv.org/abs/2311.14671
arXiv PDF paper https://arxiv.org/pdf/2311.14671.pdf
In-context segmentation aims at segmenting novel images using a few labeled example images, termed as “in-context examples”, exploring content similarities between examples and the target.
… in-context segmentation is more challenging than classic ones due to its meta-learning nature, requiring the model to learn segmentation rules conditioned on a few samples, not just the segmentation.
… propose SEGIC, an end-to-end segment-in-context framework built upon a single vision foundation model (VFM).
… SEGIC leverages the emergent correspondence within VFM to capture dense relationships between target images and in-context samples.
… information from in-context samples is then extracted into three types of instructions, i.e. geometric, visual, and meta instructions, serving as explicit conditions for the final mask prediction.
… SEGIC … yields state-of-the-art performance on one-shot segmentation benchmarks … can be easily generalized to diverse tasks, including video object segmentation and open-vocabulary segmentation …
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
