Representation of semantic context and local details is the essential issue for building modern semantic segmentation models. However, the interrelationship between semantic context and local details is not well explored in previous works. In this paper, we propose a Dynamic Dual Sampling Module (DDSM) to conduct dynamic affinity modeling and propagate semantic context to local details, which yields a more discriminative representation. Specifically, a dynamic sampling strategy is used to sparsely sample representative pixels and channels in the higher layer, forming adaptive compact support for each pixel and channel in the lower layer. The sampled features with high semantics are aggregated according to the affinities and then propagated to detailed lower-layer features, leading to a fine-grained segmentation result with well-preserved boundaries. Experiment results on both Cityscapes and Camvid datasets validate the effectiveness and efficiency of the proposed approach. Code and models will be available at \url{x3https://github.com/Fantasticarl/DDSM}.
翻译:描述语义背景和当地细节是建立现代语义分解模型的基本问题。然而,以前的工作没有很好地探讨语义背景和当地细节之间的相互关系。在本文件中,我们提议建立一个动态双重抽样模块(DDSM),以进行动态的亲和模型,并将语义背景传播给当地细节,从而产生更具有歧视性的表述。具体地说,采用动态抽样战略,在较高层次稀疏地抽样具有代表性的像素和渠道,对下层的每个像素和通道形成适应性的紧凑支持。具有高语义特征的样本根据亲和特征进行汇总,然后传播到详细的低层特征,从而产生精细的分解结果,并有完善的边界。城市景象和Camvid数据集的实验结果将证实拟议方法的有效性和效率。代码和模型将在\url{x3https://github.com/Fantasticarr/DDSM}。