本文探讨了一种实例感知语义分割的方法，通过多任务网络级联实现。文章介绍了网络架构，其中每个阶段包含损失项，并且后续阶段的训练依赖于早期阶段的输出。最终，通过五阶段推断进行优化。引用了Fast R-CNN的工作，并在测试中使用回归框作为新的提案进行进一步处理。
Dai, Jifeng, Kaiming He, and Jian Sun. “Instance-aware semantic segmentation via multitask network cascades.” arXiv preprint arXiv:1512.04412 (2015). (Citations: 40).
1. RPN. The instances can be represented by bounding boxes that are class-agnostic.
2. Estimating masks. A pixel-level mask is predicted by logistic regression for each bounding box instance. They are still class-agnostic.
3. Categorizing objects. The category-wise label is predicted for each mask-level instance.
We expect that each sub-task is simpler than the original instance segmentation task, and is more easily addressed by CNNs.
1 Motivation
All previous works require externel segmentation proposals, which are slow at test time.
2 Architecture
See Fig. We divide the task into three sub-tasks.1. RPN. The instances can be represented by bounding boxes that are class-agnostic.
2. Estimating masks. A pixel-level mask is predicted by logistic regression for each bounding box instance. They are still class-agnostic.
3. Categorizing objects. The category-wise label is predicted for each mask-level instance.
We expect that each sub-task is simpler than the original instance segmentation task, and is more easily addressed by CNNs.
最低0.47元/天 解锁文章
1405
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
