State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University,Guiyang,Guizhou,China.
PLoS One. 2022 Sep 30;17(9):e0274249. doi: 10.1371/journal.pone.0274249. eCollection 2022.
Low-level features contain spatial detail information, and high-level features contain rich semantic information. Semantic segmentation research focuses on fully acquiring and effectively fusing spatial detail with semantic information. This paper proposes a multiscale feature-enhanced adaptive fusion network named MFEAFN to improve semantic segmentation performance. First, we designed a Double Spatial Pyramid Module named DSPM to extract more high-level semantic information. Second, we designed a Focusing Selective Fusion Module named FSFM to fuse different scales and levels of feature maps. Specifically, the feature maps are enhanced to adaptively fuse these features by generating attention weights through a spatial attention mechanism and a two-dimensional discrete cosine transform, respectively. To validate the effectiveness of FSFM, we designed different fusion modules for comparison and ablation experiments. MFEAFN achieved 82.64% and 78.46% mIoU on the PASCAL VOC2012 and Cityscapes datasets. In addition, our method has better segmentation results than state-of-the-art methods.
底层特征包含空间细节信息，高层特征包含丰富的语义信息。语义分割研究集中于充分获取和有效融合空间细节与语义信息。本文提出了一种名为 MFEAFN 的多尺度特征增强自适应融合网络，以提高语义分割性能。首先，我们设计了一个名为 DSPM 的双空间金字塔模块，以提取更多的高层语义信息。其次，我们设计了一个名为 FSFM 的聚焦选择融合模块，以融合不同尺度和层次的特征图。具体来说，通过空间注意力机制和二维离散余弦变换分别生成注意力权重，对特征图进行增强以自适应地融合这些特征。为了验证 FSFM 的有效性，我们设计了不同的融合模块进行对比和消融实验。MFEAFN 在 PASCAL VOC2012 和 Cityscapes 数据集上分别实现了 82.64%和 78.46%的 mIoU。此外，我们的方法比最先进的方法具有更好的分割结果。
