ShanghaiTech University Knowledge Management System
Part-aware Prototype Network for Few-shot Semantic Segmentation | |
2020-07 | |
会议录名称 | EUROPEAN COMPUTER VISION ASSOCIATION (IF:0.402[JCR-2005],0.000[5-Year]) |
ISSN | 0302-9743 |
卷号 | 12354 LNCS |
页码 | 142-158 |
发表状态 | 已发表 |
DOI | https://link.springer.com/chapter/10.1007/978-3-030-58545-7_9 |
摘要 | Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin |
关键词 | Semantics Computer vision Semantic Web Image enhancement Graph neural networks Experimental evaluation Graph neural networks Intra-class variation Object region Semantic objects Semantic segmentation Shot segmentation Unlabeled data |
会议名称 | ECCV-2020 |
出版地 | springer |
会议地点 | Glasgow, Scotland |
会议日期 | 2020.08.26 |
URL | 查看原文 |
收录类别 | SCI ; EI |
语种 | 英语 |
出版者 | Springer Science and Business Media Deutschland GmbH |
EI入藏号 | 20204909584772 |
EI主题词 | Semantic Segmentation |
EISSN | 1611-3349 |
EI分类号 | 723 Computer Software, Data Handling and Applications ; 723.4 Artificial Intelligence ; 723.5 Computer Applications ; 741.2 Vision ; 903 Information Science |
原始文献类型 | Conference article (CA) |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/123465 |
专题 | 信息科学与技术学院_硕士生 信息科学与技术学院_PI研究组_何旭明组 信息科学与技术学院_博士生 |
共同第一作者 | Zhang XY(张相宜) |
通讯作者 | Xuming He |
作者单位 | 1.ShanghaiTech University 2.Shanghai Engineering Research Center of Intelligent Vision and Imaging |
第一作者单位 | 上海科技大学 |
通讯作者单位 | 上海科技大学 |
第一作者的第一单位 | 上海科技大学 |
推荐引用方式 GB/T 7714 | Liu YF,Zhang XY,Zhang SY,et al. Part-aware Prototype Network for Few-shot Semantic Segmentation[C]. springer:Springer Science and Business Media Deutschland GmbH,2020:142-158. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
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。