Machine learningDeep Learning, Image Segmentation, Foundation Models
Segment Anything Model
Segment Anything Model (SAM) 是 Kirillov 等人于 2023 年推出的一款基础模型，它能够根据各种形式的提示分割图像中的任何对象。SAM 在海量的多样化图像数据集上进行训练，并学会根据用户输入的少量信息（如点、框或文本描述）来分割对象。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Kirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026). DOI: 10.1109/iccv51070.2023.00371 ↗
如何引用本页
ScholarGate. (2026, June 3). A Foundation Model for Image Segmentation. ScholarGate. https://scholargate.app/zh/deep-learning/segment-anything-model
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- DETR（检测变换器）深度学习↔ compare
- 掩码自编码器深度学习↔ compare
- Swin Transformer深度学习↔ compare
- Vision Transformer深度学习↔ compare