Knowledge Commons of Institute of Automation,CAS
AHDet: A dynamic coarse-to-fine gaze strategy for active object detection | |
Xu, Nuo1,2![]() ![]() ![]() ![]() | |
发表期刊 | NEUROCOMPUTING
![]() |
ISSN | 0925-2312 |
2022-06-28 | |
卷号 | 491页码:522-532 |
摘要 | In the work setting of deep learning, most of the neural networks employed for visual object detection in recent years are based on bounding box regression. The performance of active detectors through multistep decision-making is limited by the rough model design. However, from the perspective of cognitive science, the recognition in the human visual system is a decision process from coarse to fine. Based on the theory of ``see the forest first, then the trees", this paper proposes a dynamic coarse-to-fine gaze strategy for active object detection, named AHDet, which takes the key points as the realization carrier of the coarse-to-fine concept. The detection process is divided into two steps, AIM and HIT. In the step of AIM, the positioning and prior bounding boxes for objects are given by detecting the center points, referring to the first glance. In the step of HIT, bounding boxes are dynamically adjusted to obtain compact bounding boxes with the help of the corner points, referring to the careful observation. With the design of the two-step coarse-to-fine gaze process, AHDet outperforms traditional approaches. A series of experiments performed on MS-COCO and PASCAL VOC dataset demonstrate the advantages of AHDet. (C) 2021 Elsevier B.V. All rights reserved. |
关键词 | Object detection Active object detection Deep reinforcement learning Convolutional neural networks |
DOI | 10.1016/j.neucom.2021.12.030 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[91438105] ; National Natural Science Foundation of China[62076242] ; National Natural Science Foundation of China[61976208] |
项目资助者 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000830181200010 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/49840 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Huo, Chunlei |
作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xu, Nuo,Huo, Chunlei,Zhang, Xin,et al. AHDet: A dynamic coarse-to-fine gaze strategy for active object detection[J]. NEUROCOMPUTING,2022,491:522-532. |
APA | Xu, Nuo,Huo, Chunlei,Zhang, Xin,&Pan, Chunhong.(2022).AHDet: A dynamic coarse-to-fine gaze strategy for active object detection.NEUROCOMPUTING,491,522-532. |
MLA | Xu, Nuo,et al."AHDet: A dynamic coarse-to-fine gaze strategy for active object detection".NEUROCOMPUTING 491(2022):522-532. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
AHDet A dynamic coar(2664KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论