| Title: | Multiple-Attention Mechanism Network for Semantic Segmentation |
| Author(s): | Wang D; Xiang S; Zhou Y; Mu J; Zhou H; Irampaye R; |
| Address: | "School of Automation and Electronic Information, Xiangtan University, Xiangtan 411105, China. Shanghai Aerospace Control Technology Institute, Shanghai 201109, China. School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, China" |
| ISSN/ISBN: | 1424-8220 (Electronic) 1424-8220 (Linking) |
| Abstract: | "Contextual information and the dependencies between dimensions is vital in image semantic segmentation. In this paper, we propose a multiple-attention mechanism network (MANet) for semantic segmentation in a very effective and efficient way. Concretely, the contributions are as follows: (1) a novel dual-attention mechanism for capturing feature dependencies in spatial and channel dimensions, where the adjacent position attention captures the dependencies between pixels well; (2) a new cross-dimensional interactive attention feature fusion module, which strengthens the fusion of fine location structure information in low-level features and category semantic information in high-level features. We conduct extensive experiments on semantic segmentation benchmarks including PASCAL VOC 2012 and Cityscapes datasets. Our MANet achieves the mIoU scores of 75.5% and 72.8% on PASCAL VOC 2012 and Cityscapes datasets, respectively. The effectiveness of the network is higher than the previous popular semantic segmentation networks under the same conditions" |
| Keywords: | "Image Processing, Computer-Assisted/methods *Neural Networks, Computer Semantics *Volatile Organic Compounds adjacent position attention attention mechanism cross-dimensional interactive semantic segmentation;" |
| Notes: | "MedlineWang, Dongli Xiang, Shengliang Zhou, Yan Mu, Jinzhen Zhou, Haibin Irampaye, Richard eng 61773330/National Natural Science Foundation of China/ Switzerland 2022/06/25 Sensors (Basel). 2022 Jun 13; 22(12):4477. doi: 10.3390/s22124477" |
