Task-aware adaptive attention learning for few-shot semantic segmentation
文献类型：期刊论文
| 作者 | Mao, Binjie1,2 ; Wang, Lingfeng1,2; Xiang, Shiming1,2; Pan, Chunhong2
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2022-07-14 |
| 卷号 | 494页码:104-115 |
| 关键词 | Few-shot semantic segmentation Adaptive feature learning Attention mechanism Task-aware |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2022.04.089 |
| 通讯作者 | Wang, Lingfeng(lfwang@nlpr.ia.ac.cn) |
| 英文摘要 | Few-shot semantic segmentation is a newly developing and challenging computer vision task which aims to predict pixel-wise segmentation on the novel categories where only a few annotated samples are supplied. Because of the scarcity of the annotated novel class samples, the main obstacle of this issue is the diversity of objects in the support set and query set. This paper proposes a novel network aiming to bridge the gap by exploring the correlation between the support feature and the query feature. Specifically, a task-aware adaptive attention module(TAAM) is introduced to extract the task-specific information from the current input and integrates it into the feature representations both in channel dimension and spatial dimension for adaptive reinforcement. Besides, an additional prediction refinement module(RPM) is attached to further optimize the predictions to present more details of objects. Furthermore, through a non-parameter aggregation operation, the proposed network is easy to generalize to k-shot segmentation without developing specific architectures. Extensive experiments on three benchmarks demonstrate that our method exceeds previous state-of-the-arts with a sizable margin, verifying the effectiveness of the proposed method. (C) 2022 Elsevier B.V. All rights reserved. |
| WOS关键词 | NETWORK |
| 资助项目 | National Key Research and Development Program of China[2018-AAA0100400] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[61976208] ; National Natural Science Foundation of China[62076242] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000830184400010 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/49755]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 通讯作者 | Wang, Lingfeng |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Dept Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Mao, Binjie,Wang, Lingfeng,Xiang, Shiming,et al. Task-aware adaptive attention learning for few-shot semantic segmentation[J]. NEUROCOMPUTING,2022,494:104-115. |
| APA | Mao, Binjie,Wang, Lingfeng,Xiang, Shiming,&Pan, Chunhong.(2022).Task-aware adaptive attention learning for few-shot semantic segmentation.NEUROCOMPUTING,494,104-115. |
| MLA | Mao, Binjie,et al."Task-aware adaptive attention learning for few-shot semantic segmentation".NEUROCOMPUTING 494(2022):104-115. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
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。