Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to predict semantic labels around the object boundaries, thus FCN-based methods usually produce parsing results with inaccurate boundaries. Meanwhile, many works have demonstrate that level set based active contours are superior to the boundary estimation in sub-pixel accuracy. However, they are quite sensitive to initial settings. To address these limitations, in this paper we propose a novel Deep Multiphase Level Set (DMLS) method for semantic scene parsing, which efficiently incorporates multiphase level sets into deep neural networks. The proposed method consists of three modules, i.e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning. More specifically, recurrent FCNs learn multi-level representations of input images with different contexts. Adaptive multiphase level set drives the discriminative contour for each semantic class, which makes use of the advantages of both global and local information. In each time-step of the recurrent FCNs, deeply supervised learning is incorporated for model training. Extensive experiments on three public benchmarks have shown that our proposed method achieves new state-of-the-art performances. The source codes will be released at https://github.com/Pchank/DMLS-for-SSP.

中文翻译：

---

用于场景解析的深度多相级别集。


最近，全卷积网络（FCN）似乎成为图像分割（包括语义场景解析）的首选架构。然而，通用的 FCN 很难预测对象边界周围的语义标签，因此基于 FCN 的方法通常会产生边界不准确的解析结果。同时，许多工作已经证明基于水平集的活动轮廓在亚像素精度方面优于边界估计。然而，它们对初始设置非常敏感。为了解决这些限制，在本文中，我们提出了一种用于语义场景解析的新型深度多相水平集（DMLS）方法，该方法有效地将多相水平集合并到深度神经网络中。该方法由三个模块组成，即循环FCN、自适应多相水平集和深度监督学习。更具体地说，循环 FCN 学习具有不同上下文的输入图像的多级表示。自适应多相水平集驱动每个语义类别的判别轮廓，它利用了全局和局部信息的优点。在循环 FCN 的每个时间步中，深度监督学习都被纳入模型训练中。对三个公共基准的广泛实验表明，我们提出的方法实现了新的最先进的性能。源代码将在 https://github.com/Pchank/DMLS-for-SSP 发布。