Interaction semantic segmentation network via progressive supervised learning
文献类型:期刊论文
作者 | Zhao, Ruini2; Xie, Meilin2; Feng, Xubin2; Guo, Min2; Su, Xiuqin2; Zhang, Ping1 |
刊名 | MACHINE VISION AND APPLICATIONS |
出版日期 | 2024-03 |
卷号 | 35期号:2 |
ISSN号 | 0932-8092;1432-1769 |
关键词 | Semantic segmentation Boundary refinement Progressive supervised learning Information interaction |
DOI | 10.1007/s00138-023-01500-4 |
产权排序 | 1 |
英文摘要 | Semantic segmentation requires both low-level details and high-level semantics, without losing too much detail and ensuring the speed of inference. Most existing segmentation approaches leverage low- and high-level features from pre-trained models. We propose an interaction semantic segmentation network via Progressive Supervised Learning (ISSNet). Unlike a simple fusion of two sets of features, we introduce an information interaction module to embed semantics into image details, they jointly guide the response of features in an interactive way. We develop a simple yet effective boundary refinement module to provide refined boundary features for matching corresponding semantic. We introduce a progressive supervised learning strategy throughout the training level to significantly promote network performance, not architecture level. Our proposed ISSNet shows optimal inference time. We perform extensive experiments on four datasets, including Cityscapes, HazeCityscapes, RainCityscapes and CamVid. In addition to performing better in fine weather, proposed ISSNet also performs well on rainy and foggy days. We also conduct ablation study to demonstrate the role of our proposed component. Code is available at: https://github.com/Ruini94/ISSNet |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:001156034900001 |
源URL | [http://ir.opt.ac.cn/handle/181661/97211] |
专题 | 西安光学精密机械研究所_光电测量技术实验室 |
通讯作者 | Feng, Xubin |
作者单位 | 1.Changan Univ, Xian 710064, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Zhao, Ruini,Xie, Meilin,Feng, Xubin,et al. Interaction semantic segmentation network via progressive supervised learning[J]. MACHINE VISION AND APPLICATIONS,2024,35(2). |
APA | Zhao, Ruini,Xie, Meilin,Feng, Xubin,Guo, Min,Su, Xiuqin,&Zhang, Ping.(2024).Interaction semantic segmentation network via progressive supervised learning.MACHINE VISION AND APPLICATIONS,35(2). |
MLA | Zhao, Ruini,et al."Interaction semantic segmentation network via progressive supervised learning".MACHINE VISION AND APPLICATIONS 35.2(2024). |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。