论文标题
STDC-MA语义细分网络
STDC-MA Network for Semantic Segmentation
论文作者
论文摘要
语义细分广泛地应用于自主驾驶和智能运输中，其方法高度要求空间和语义信息。在这里，提出了一个STDC-MA网络来满足这些需求。首先，在STDC-MA中采用了STDC-SEG结构，以确保轻巧有效的结构。随后，应用特征对齐模块（FAM）来了解高级和低级特征之间的偏移，从而解决了与高级特征映射上的上采样相关的像素偏移问题。我们的方法实现了高级功能和低级功能之间的有效融合。采用了分层的多尺度注意机制来揭示一个图像的两个不同输入尺寸的注意区域之间的关系。通过这种关系，受到很多关注的地区被整合到分段结果中，从而减少了输入图像的未关注区域并改善了多尺度特征的有效利用。 STDC- MA将分割速度保持为STDC-SEG网络，同时提高小对象的分割精度。在CityScapes的验证集中验证了STDC-MA。 STDC-MA的分割结果达到76.81％，输入为0.5倍，比STDC-SEG高3.61％。
Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the STDC-Seg structure is employed in STDC-MA to ensure a lightweight and efficient structure. Subsequently, the feature alignment module (FAM) is applied to understand the offset between high-level and low-level features, solving the problem of pixel offset related to upsampling on the high-level feature map. Our approach implements the effective fusion between high-level features and low-level features. A hierarchical multiscale attention mechanism is adopted to reveal the relationship among attention regions from two different input sizes of one image. Through this relationship, regions receiving much attention are integrated into the segmentation results, thereby reducing the unfocused regions of the input image and improving the effective utilization of multiscale features. STDC- MA maintains the segmentation speed as an STDC-Seg network while improving the segmentation accuracy of small objects. STDC-MA was verified on the verification set of Cityscapes. The segmentation result of STDC-MA attained 76.81% mIOU with the input of 0.5x scale, 3.61% higher than STDC-Seg.
