中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Att-FPA: Boosting Feature Perceive for Object Detection

文献类型：期刊论文

作者Liu, Jingwei1,2; Gu, Yi3; Han, Shumin3; Zhang, Zhibin1,2; Guo, Jiafeng1,2; Cheng, Xueqi1,2
刊名IEEE ACCESS
出版日期2021
卷号9页码:47380-47390
ISSN号2169-3536
关键词Feature extraction Location awareness Task analysis Object detection Proposals Neck Semantics Deep learning computer vision object detection attention feature representation
DOI10.1109/ACCESS.2021.3068488
英文摘要The deep convolutional networks have a great success in vision classification tasks. For object detection, tasks are divided into two subtasks: localization and classification. The detectors scan the whole image to generate object proposals relying on the predefined anchors or points, then classify and fine trim the proposals. The localization task plays an important role in object detection. The foreground objects and background can be easily confused under complex scenes in the existing approaches. Thus, the localization task results in a bad influence on the performance of classification problems. In order to enhance the object localization perceived, a novel method called Attentional Feature Perceive and Augmentation (Att-FPA) is constructed, which devotes setting up a feature dual perceive for localization and classification. Firstly, an attention mask branch (with an attention mask) is imported to check out if the detecting area is the background or containing one or more objects. By maintaining the feature representation of background, the attention mask is employed to strengthen the feature representation of foreground objects, which significantly enhances the localization perceived ability of objects. Moreover, Att-FPA supplies a novel way on feature re-extraction and augmentation, which further promotes the performance significantly. In the task of Ms COCO object detection, Att-FPA achieves an outstanding promotion(3.0+ mAP) than baseline (Faster-Rcnn) method. It establishes a new efficient method of feature representation, which outperforms the state-of-the-art models in object detection.
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000637183800001
源URL[http://119.78.100.204/handle/2XEOYT63/16773]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Han, Shumin
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China
3.Baidu Online Network Technol Beijing Co Ltd, Beijing 101399, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Jingwei,Gu, Yi,Han, Shumin,et al. Att-FPA: Boosting Feature Perceive for Object Detection[J]. IEEE ACCESS,2021,9:47380-47390.
APA Liu, Jingwei,Gu, Yi,Han, Shumin,Zhang, Zhibin,Guo, Jiafeng,&Cheng, Xueqi.(2021).Att-FPA: Boosting Feature Perceive for Object Detection.IEEE ACCESS,9,47380-47390.
MLA Liu, Jingwei,et al."Att-FPA: Boosting Feature Perceive for Object Detection".IEEE ACCESS 9(2021):47380-47390.

入库方式： OAI收割

来源：计算技术研究所

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。