Machine learningObject detection / segmentation
Mask R-CNN：具有像素级掩码的实例分割
Mask R-CNN 是 Facebook AI Research (FAIR) 的 Kaiming He、Georgia Gkioxari、Piotr Dollár 和 Ross Girshick 于 2017 年提出的一个用于实例分割的深度学习框架。它通过添加一个并行分支来扩展 Faster R-CNN，该分支为每个检测到的对象实例预测一个二值的像素级掩码，从而能够在单次前向传播中同时完成对象检测、分类和细粒度分割。
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
- He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. IEEE International Conference on Computer Vision (ICCV), 2980–2988. DOI: 10.1109/ICCV.2017.322 ↗
如何引用本页
ScholarGate. (2026, June 2). Mask R-CNN (Instance Segmentation). ScholarGate. https://scholargate.app/zh/deep-learning/mask-rcnn
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.
Compare side by side →