Verified65% confidenceFactExact time
SAM (Segment Anything Model) is a model open-sourced by Meta that achieves zero-shot segmentation of arbitrary objects through large-scale pre-training on 11 million images and 1 billion masks.
3
Sources
65%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
AI自动化OSINT实战：CS背景者的学习路径与工具选择
Related Claims
UnverifiedSAM, developed by Meta, can perform zero-shot segmentation of any object in an image; its core innovation is framing segmentation as a promptable, interactive problem.74% similarUnverifiedSegment Anything（SAM）是Meta推出的通用图像分割基础模型，能够零样本分割任意物体73% similarVerifiedMeta's research division developed models such as SAM (Segment Anything Model) and ImageBind.71% similarUnverifiedThe SAM series is a general-purpose image segmentation model released by Meta; its core concept is to segment everything, capable of segmenting any object in an image without training on specific categories.70% similarUnverifiedMeta 的 Segment Anything Model（SAM）将高质量智能抠像能力完全开源化70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501928API
curl https://kongchang.com/api/v1/knowledge/claims/501928MCP
get_claim(id=501928)