Zhang Pingping, Liu Wei, Lei Yinjie, Wang Hongyu, Lu Huchuan
IEEE Trans Image Process. 2020 Feb 19. doi: 10.1109/TIP.2019.2957915.
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.
最近，全卷积网络（FCN）似乎已成为图像分割（包括语义场景解析）的首选架构。然而，通用的FCN很难预测物体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，许多研究表明基于水平集的主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。为了解决这些局限性，在本文中我们提出了一种用于语义场景解析的新颖的深度多相水平集（DMLS）方法，该方法有效地将多相水平集纳入深度神经网络。所提出的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。自适应多相水平集为每个语义类驱动判别轮廓，它利用了全局和局部信息的优势。在循环FCN的每个时间步中，纳入深度监督学习进行模型训练。在三个公共基准上进行的大量实验表明，我们提出的方法取得了新的最先进性能。源代码将在https://github.com/Pchank/DMLS-for-SSP上发布。
