论文标题
使用迭代金字塔环境的联合语义分割和边界检测
Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
论文作者
论文摘要
在本文中，我们提出了一个共同的多任务学习框架，用于语义分割和边界检测。框架中的关键组成部分是迭代金字塔上下文模块（PCM），它将两个任务并存储共享的潜在语义，以在两个任务之间进行交互。对于语义边界检测，我们提出了新型的空间梯度融合以抑制非语言边缘。由于语义边界检测是语义分割的双重任务，因此我们引入了具有边界一致性约束的损耗函数，以提高语义分割的边界像素精度。我们的广泛实验表明，不仅在语义分段，而且在语义边界检测中，都表明了优于最先进的作品。特别是，在不使用粗数据或任何外部数据进行语义细分的情况下，可以实现城市景观测试集的平均得分81：8％。对于语义边界检测，就AP而言，我们比以前的最新作品提高了9.9％，而MF（ODS）则提高了6：8％。
In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. The critical component in the framework is the iterative pyramid context module (PCM), which couples two tasks and stores the shared latent semantics to interact between the two tasks. For semantic boundary detection, we propose the novel spatial gradient fusion to suppress nonsemantic edges. As semantic boundary detection is the dual task of semantic segmentation, we introduce a loss function with boundary consistency constraint to improve the boundary pixel accuracy for semantic segmentation. Our extensive experiments demonstrate superior performance over state-of-the-art works, not only in semantic segmentation but also in semantic boundary detection. In particular, a mean IoU score of 81:8% on Cityscapes test set is achieved without using coarse data or any external data for semantic segmentation. For semantic boundary detection, we improve over previous state-of-the-art works by 9.9% in terms of AP and 6:8% in terms of MF(ODS).
