Robust one-stage object detection with location-aware classifiers

doi:10.1016/j.patcog.2020.107334

	Robust one-stage object detection with location-aware classifiers
	Chen, Qiang1,2 ; Wang, Peisong1 ; Cheng, Anda 1,2; Wang, Wanguo 4; Zhang, Yifan1,2 ; Cheng, Jian1,2,3
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2020-09-01
卷号	105 页码:11
通讯作者	Cheng, Jian(jcheng@nlpr.ia.ac.cn)
摘要	Recent progress on one-stage detectors focuses on improving the quality of bounding boxes, while they pay less attention to the classification head. In this work, we focus on investigating the influence of the classification head. To understand the behavior of the classifier in one-stage detectors, we resort to the methods of the Explainable deep learning area. We visualize its learned representations via activation maps and analyze its robustness to image scene context. Based on the analysis, we observe that the classifier limits the performance of the detector due to its limited receptive field and the lack of object locations. Then, we design a simple but efficient location-aware multi-dilation module (LAMD) to enhance the weak classifier. We conduct extensive experiments on the COCO benchmark to validate the effectiveness of LAMD. The results suggest that our LAMD can achieve consistent improvements and leads to robust detection across various one-stage detectors with different backbones. (C) 2020 Elsevier Ltd. All rights reserved.
关键词	Object detetion Classification Localization Feature visualization Receptive field
DOI	10.1016/j.patcog.2020.107334
收录类别	SCI
语种	英语
资助项目	Statc Grid Corporation Projcct Development and Application of Electric Power Patrol Robot Based on Artificial Intelligence Technology
项目资助者	Statc Grid Corporation Projcct Development and Application of Electric Power Patrol Robot Based on Artificial Intelligence Technology
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000539457100021
出版者	ELSEVIER SCI LTD
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：19[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40081
专题	复杂系统认知与决策实验室_高效智能计算与学习
通讯作者	Cheng, Jian
作者单位	1.Chinese Acad Sci, Inst Automat, NLPR, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 4.State Grid Intelligence Technol Co Ltd, Jinan 250132, Shandong, 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	Chen, Qiang,Wang, Peisong,Cheng, Anda,et al. Robust one-stage object detection with location-aware classifiers[J]. PATTERN RECOGNITION,2020,105:11.
APA	Chen, Qiang,Wang, Peisong,Cheng, Anda,Wang, Wanguo,Zhang, Yifan,&Cheng, Jian.(2020).Robust one-stage object detection with location-aware classifiers.PATTERN RECOGNITION,105,11.
MLA	Chen, Qiang,et al."Robust one-stage object detection with location-aware classifiers".PATTERN RECOGNITION 105(2020):11.

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
Robust One-stage Obj（3831KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览