文献类型：期刊文献

英文题名：Cross-CBAM: a lightweight network for real-time scene segmentation

作者：Zhang, Zhengbin[1];Xu, Zhenhao[1];Gu, Xingsheng[1];Xiong, Juan[2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, MeiLong Rd, Shanghai 200237, Peoples R China;[2]Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, JunGon Rd, Shanghai 200093, Peoples R China

年份：2024

卷号：21

期号：2

外文期刊名：JOURNAL OF REAL-TIME IMAGE PROCESSING

收录：;EI(收录号：20240915638170);WOS:【SCI-EXPANDED(收录号:WOS:001169796400001)】；

基金：No Statement Available

语种：英文

外文关键词：Real-time semantic segmentation; Scene segmentation; Deep learning; Attention mechanism

摘要：Real-time semantic segmentation poses a significant challenge in scene parsing. Despite traditional semantic segmentation networks have made remarkable leap-forwards in semantic accuracy, the performance of inference speed remains unsatisfactory. This paper introduces the Cross-CBAM network, a novel lightweight architecture designed for real-time semantic segmentation. Specifically, a Squeeze-and-Excitation Atrous Spatial Pyramid Pooling Module (SE-ASPP) is proposed to obtain variable field-of-view and multiscale information. Additionally, we propose a Cross Convolutional Block Attention Module (CCBAM), wherein a cross-multiply operation guides low-level detail information with high-level semantic information. Unlike previous approaches that leverage attention to concentrate on the relevant information in the backbone, CCBAM utilizes cross-attention for feature fusion within the Feature Pyramid Network (FPN) structure. Extensive experiments on the Cityscapes dataset and Camvid dataset demonstrate the effectiveness of the proposed Cross-CBAM model by achieving a promising trade-off between segmentation accuracy and inference speed. On the Cityscapes test set, we achieve 73.4% mIoU with a speed of 240.9 FPS and 77.2% mIoU with a speed of 88.6 FPS on NVIDIA GTX 1080Ti.