Att-FPA: Boosting Feature Perceive for Object Detection

doi:10.1109/ACCESS.2021.3068488

	Att-FPA: Boosting Feature Perceive for Object Detection
	Liu, Jingwei 1,2; Gu, Yi 3; Han, Shumin 3; Zhang, Zhibin 1,2; Guo, Jiafeng 1,2; Cheng, Xueqi 1,2
	2021
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	9 页码:47380-47390
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.
关键词	Feature extraction Location awareness Task analysis Object detection Proposals Neck Semantics Deep learning computer vision object detection attention feature representation
DOI	10.1109/ACCESS.2021.3068488
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000637183800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16774
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.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, 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.