A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering

• DOI: 10.48550/arxiv.2306.06211
• Publication Date: 2023-01-01
• Authors: Chaoning Zhang; Sheng Zheng; Chenghao Li; Yu Qiao; Taegoo Kang; Xinru Shan; Chenshuang Zhang; Caiyan Qin; François Rameau; Sung‐Ho Bae; Choong Seon Hong
• Keywords: Market Segmentation; Foundation (evidence)

Segment anything model (SAM) developed by Meta AI Research has recently attracted significant attention. Trained on a large segmentation dataset of over 1 billion masks, SAM is capable segmenting any object certain image. In the original work, authors turned to zero-short transfer tasks (like edge detection) for evaluating performance SAM. Recently, numerous works have attempted investigate in various scenarios recognize and segment objects. Moreover, projects emerged show versatility as foundation combining it with other models, like Grounding DINO, Stable Diffusion, ChatGPT, etc. With relevant papers increasing exponentially, challenging readers catch up development To this end, work conducts first yet comprehensive survey This an ongoing project we intend update manuscript regular basis. Therefore, are welcome contact us if they complete new related so that can include them our next version.