【摘要】 虽然图像语义分割因其有助于更好地分析和理解图像而被广泛应用于多个领域,但是基于全卷积神经网络的模型在语义分割方面依然存在分辨率重构及如何利用上下文信息的问题.因此,文中提出基于语义传播与前/背景感知的图像语义分割网络.首先,提出联合语义传播上采样模块,提取高层特征的全局语义信息与局部语义信息,用于得到语义权重,将高层特征语义传播到低层特征,缩小两者之间的语义差距,再通过逐层上采样实现分辨率重构.此外,还提出金字塔前/背景感知模块,通过两个并行分支提取不同尺度前景特征与背景特征,建立前景与背景间的依赖关系,捕获多尺度的前/背景感知特征,增强前景特征的上下文表示.语义分割基准数据集上的实验表明,文中网络性能较优.更多还原

【Abstract】 Although image segmentation is widely applied in many fields owing to the assistance of better analysis and understanding of images, the models based on fully convolutional neural networks still engender the problems of resolution reconstruction and contextual information usage in semantic segmentation. Aiming at the problems, a semantic propagation and fore-background aware network for image semantic segmentation is proposed. A joint semantic propagation up-sampling module(JSPU) is proposed to obtain semantic weights by extracting the global and local semantic information from high-level features. Then the semantic information is propagated from high-level features to low-level features for alleviating the semantic gap between them. The resolution reconstruction is achieved through a hierarchical up-sampling structure. In addition, a pyramid fore-background aware module is proposed to extract foreground and background features of different scales through two parallel branches. Multi-scale fore-background aware features are captured by establishing the dependency relationships between the foreground and background features, thereby the contextual representation of foreground features is enhanced. Experiments on semantic segmentation benchmark datasets show that SPAFBA is superior in performance.更多还原