SpaceMeshLab: 空间环境回移和语义分割的Meshgrid暴动共识 (SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation)

from arxiv, 5 pages, 3 figures, 4 tables. To appear in the proceedings of the 28th IEEE International Conference on Image Processing (IEEE - ICIP), September 19-22, 2021, Anchorage, Alaska, USA

Semantic segmentation networks adopt transfer learning from image classification networks which occurs a shortage of spatial context information. For this reason, we propose Spatial Context Memoization (SpaM), a bypassing branch for spatial context by retaining the input dimension and constantly communicating its spatial context and rich semantic information mutually with the backbone network. Multi-scale context information for semantic segmentation is crucial for dealing with diverse sizes and shapes of target objects in the given scene. Conventional multi-scale context scheme adopts multiple effective receptive fields by multiple dilation rates or pooling operations, but often suffer from misalignment problem with respect to the target pixel. To this end, we propose Meshgrid Atrous Convolution Consensus (MetroCon^2) which brings multi-scale scheme into fine-grained multi-scale object context using convolutions with meshgrid-like scattered dilation rates. SpaceMeshLab (ResNet-101 + SpaM + MetroCon^2) achieves 82.0% mIoU in Cityscapes test and 53.5% mIoU on Pascal-Context validation set.

翻译：语义分解网络采用图像分类网络的传导学习方法,而图像分类网络造成空间背景信息短缺。为此,我们提议采用空间环境代谢(SpaM),这是一个空间背景绕行分支,保留输入维度,与主干网络不断交流空间背景和丰富的语义信息。语义分解多尺度背景信息对于处理特定场景中目标物体的不同大小和形状至关重要。常规多尺度的多尺度环境方案通过多种变相率或集合操作,采用多重有效接收域,但往往在目标像素方面出现误点问题。为此,我们提议采用Meshgrid Atroculturation共识(Metrocon=2),将多尺度计划引入精细的多尺度天体环境,使用类似于星格分散的熔化速率进行演进。 SpaceMeshLab(ResNet-101+ SpaM + Metrocon ⁇ 2)在市景测试中达到82.0% MIOU,在帕斯卡-context确认器上达到53.5% mIoU。