DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection

Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its comput...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Beomyeon Hwang [verfasserIn] Sanghun Lee [verfasserIn] Hyunho Han [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid

Übergeordnetes Werk:	In: Applied Sciences - MDPI AG, 2012, 13(2023), 3, p 1841
Übergeordnetes Werk:	volume:13 ; year:2023 ; number:3, p 1841

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/app13031841

Katalog-ID:	DOAJ080682839

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ080682839
003	DE-627
005	20240413070706.0
007	cr uuu---uuuuu
008	230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/app13031841 \|2 doi
035			\|a (DE-627)DOAJ080682839
035			\|a (DE-599)DOAJ16603bd40eef4479946621b142ce0307
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TA1-2040
050		0	\|a QH301-705.5
050		0	\|a QC1-999
050		0	\|a QD1-999
100	0		\|a Beomyeon Hwang \|e verfasserin \|4 aut
245	1	0	\|a DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
264		1	\|c 2023
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.
650		4	\|a convolutional neural network
650		4	\|a dual-path lightweight module
650		4	\|a object detection
650		4	\|a fully convolutional one-stage object detector
650		4	\|a feature pyramid
653		0	\|a Technology
653		0	\|a T
653		0	\|a Engineering (General). Civil engineering (General)
653		0	\|a Biology (General)
653		0	\|a Physics
653		0	\|a Chemistry
700	0		\|a Sanghun Lee \|e verfasserin \|4 aut
700	0		\|a Hyunho Han \|e verfasserin \|4 aut
773	0	8	\|i In \|t Applied Sciences \|d MDPI AG, 2012 \|g 13(2023), 3, p 1841 \|w (DE-627)737287640 \|w (DE-600)2704225-X \|x 20763417 \|7 nnns
773	1	8	\|g volume:13 \|g year:2023 \|g number:3, p 1841
856	4	0	\|u https://doi.org/10.3390/app13031841 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/16603bd40eef4479946621b142ce0307 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2076-3417/13/3/1841 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2076-3417 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_171
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2055
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 13 \|j 2023 \|e 3, p 1841

Indexfelder

author_variant	b h bh s l sl h h hh
matchkey_str	article:20763417:2023----::lfoefcetulahihwihmdlfrulcnou
hierarchy_sort_str	2023
callnumber-subject-code	TA
publishDate	2023
allfields	10.3390/app13031841 doi (DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307 DE-627 ger DE-627 rakwb eng TA1-2040 QH301-705.5 QC1-999 QD1-999 Beomyeon Hwang verfasserin aut DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study. convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry Sanghun Lee verfasserin aut Hyunho Han verfasserin aut In Applied Sciences MDPI AG, 2012 13(2023), 3, p 1841 (DE-627)737287640 (DE-600)2704225-X 20763417 nnns volume:13 year:2023 number:3, p 1841 https://doi.org/10.3390/app13031841 kostenfrei https://doaj.org/article/16603bd40eef4479946621b142ce0307 kostenfrei https://www.mdpi.com/2076-3417/13/3/1841 kostenfrei https://doaj.org/toc/2076-3417 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 13 2023 3, p 1841
spelling	10.3390/app13031841 doi (DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307 DE-627 ger DE-627 rakwb eng TA1-2040 QH301-705.5 QC1-999 QD1-999 Beomyeon Hwang verfasserin aut DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study. convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry Sanghun Lee verfasserin aut Hyunho Han verfasserin aut In Applied Sciences MDPI AG, 2012 13(2023), 3, p 1841 (DE-627)737287640 (DE-600)2704225-X 20763417 nnns volume:13 year:2023 number:3, p 1841 https://doi.org/10.3390/app13031841 kostenfrei https://doaj.org/article/16603bd40eef4479946621b142ce0307 kostenfrei https://www.mdpi.com/2076-3417/13/3/1841 kostenfrei https://doaj.org/toc/2076-3417 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 13 2023 3, p 1841
allfields_unstemmed	10.3390/app13031841 doi (DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307 DE-627 ger DE-627 rakwb eng TA1-2040 QH301-705.5 QC1-999 QD1-999 Beomyeon Hwang verfasserin aut DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study. convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry Sanghun Lee verfasserin aut Hyunho Han verfasserin aut In Applied Sciences MDPI AG, 2012 13(2023), 3, p 1841 (DE-627)737287640 (DE-600)2704225-X 20763417 nnns volume:13 year:2023 number:3, p 1841 https://doi.org/10.3390/app13031841 kostenfrei https://doaj.org/article/16603bd40eef4479946621b142ce0307 kostenfrei https://www.mdpi.com/2076-3417/13/3/1841 kostenfrei https://doaj.org/toc/2076-3417 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 13 2023 3, p 1841
allfieldsGer	10.3390/app13031841 doi (DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307 DE-627 ger DE-627 rakwb eng TA1-2040 QH301-705.5 QC1-999 QD1-999 Beomyeon Hwang verfasserin aut DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study. convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry Sanghun Lee verfasserin aut Hyunho Han verfasserin aut In Applied Sciences MDPI AG, 2012 13(2023), 3, p 1841 (DE-627)737287640 (DE-600)2704225-X 20763417 nnns volume:13 year:2023 number:3, p 1841 https://doi.org/10.3390/app13031841 kostenfrei https://doaj.org/article/16603bd40eef4479946621b142ce0307 kostenfrei https://www.mdpi.com/2076-3417/13/3/1841 kostenfrei https://doaj.org/toc/2076-3417 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 13 2023 3, p 1841
allfieldsSound	10.3390/app13031841 doi (DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307 DE-627 ger DE-627 rakwb eng TA1-2040 QH301-705.5 QC1-999 QD1-999 Beomyeon Hwang verfasserin aut DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study. convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry Sanghun Lee verfasserin aut Hyunho Han verfasserin aut In Applied Sciences MDPI AG, 2012 13(2023), 3, p 1841 (DE-627)737287640 (DE-600)2704225-X 20763417 nnns volume:13 year:2023 number:3, p 1841 https://doi.org/10.3390/app13031841 kostenfrei https://doaj.org/article/16603bd40eef4479946621b142ce0307 kostenfrei https://www.mdpi.com/2076-3417/13/3/1841 kostenfrei https://doaj.org/toc/2076-3417 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 13 2023 3, p 1841
language	English
source	In Applied Sciences 13(2023), 3, p 1841 volume:13 year:2023 number:3, p 1841
sourceStr	In Applied Sciences 13(2023), 3, p 1841 volume:13 year:2023 number:3, p 1841
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid Technology T Engineering (General). Civil engineering (General) Biology (General) Physics Chemistry
isfreeaccess_bool	true
container_title	Applied Sciences
authorswithroles_txt_mv	Beomyeon Hwang @@aut@@ Sanghun Lee @@aut@@ Hyunho Han @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	737287640
id	DOAJ080682839
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ080682839</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413070706.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/app13031841</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ080682839</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ16603bd40eef4479946621b142ce0307</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TA1-2040</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QH301-705.5</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QC1-999</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QD1-999</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Beomyeon Hwang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">dual-path lightweight module</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">fully convolutional one-stage object detector</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature pyramid</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Technology</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">T</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Engineering (General). Civil engineering (General)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Biology (General)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Physics</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Chemistry</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sanghun Lee</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Hyunho Han</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Applied Sciences</subfield><subfield code="d">MDPI AG, 2012</subfield><subfield code="g">13(2023), 3, p 1841</subfield><subfield code="w">(DE-627)737287640</subfield><subfield code="w">(DE-600)2704225-X</subfield><subfield code="x">20763417</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:13</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:3, p 1841</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/app13031841</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/16603bd40eef4479946621b142ce0307</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2076-3417/13/3/1841</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2076-3417</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">13</subfield><subfield code="j">2023</subfield><subfield code="e">3, p 1841</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Beomyeon Hwang
spellingShingle	Beomyeon Hwang misc TA1-2040 misc QH301-705.5 misc QC1-999 misc QD1-999 misc convolutional neural network misc dual-path lightweight module misc object detection misc fully convolutional one-stage object detector misc feature pyramid misc Technology misc T misc Engineering (General). Civil engineering (General) misc Biology (General) misc Physics misc Chemistry DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
authorStr	Beomyeon Hwang
ppnlink_with_tag_str_mv	@@773@@(DE-627)737287640
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TA1-2040
illustrated	Not Illustrated
issn	20763417
topic_title	TA1-2040 QH301-705.5 QC1-999 QD1-999 DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection convolutional neural network dual-path lightweight module object detection fully convolutional one-stage object detector feature pyramid
topic	misc TA1-2040 misc QH301-705.5 misc QC1-999 misc QD1-999 misc convolutional neural network misc dual-path lightweight module misc object detection misc fully convolutional one-stage object detector misc feature pyramid misc Technology misc T misc Engineering (General). Civil engineering (General) misc Biology (General) misc Physics misc Chemistry
topic_unstemmed	misc TA1-2040 misc QH301-705.5 misc QC1-999 misc QD1-999 misc convolutional neural network misc dual-path lightweight module misc object detection misc fully convolutional one-stage object detector misc feature pyramid misc Technology misc T misc Engineering (General). Civil engineering (General) misc Biology (General) misc Physics misc Chemistry
topic_browse	misc TA1-2040 misc QH301-705.5 misc QC1-999 misc QD1-999 misc convolutional neural network misc dual-path lightweight module misc object detection misc fully convolutional one-stage object detector misc feature pyramid misc Technology misc T misc Engineering (General). Civil engineering (General) misc Biology (General) misc Physics misc Chemistry
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Applied Sciences
hierarchy_parent_id	737287640
hierarchy_top_title	Applied Sciences
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)737287640 (DE-600)2704225-X
title	DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
ctrlnum	(DE-627)DOAJ080682839 (DE-599)DOAJ16603bd40eef4479946621b142ce0307
title_full	DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
author_sort	Beomyeon Hwang
journal	Applied Sciences
journalStr	Applied Sciences
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Beomyeon Hwang Sanghun Lee Hyunho Han
container_volume	13
class	TA1-2040 QH301-705.5 QC1-999 QD1-999
format_se	Elektronische Aufsätze
author-letter	Beomyeon Hwang
doi_str_mv	10.3390/app13031841
author2-role	verfasserin
title_sort	dlmfcos: efficient dual-path lightweight module for fully convolutional object detection
callnumber	TA1-2040
title_auth	DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
abstract	Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.
abstractGer	Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.
abstract_unstemmed	Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_171 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	3, p 1841
title_short	DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection
url	https://doi.org/10.3390/app13031841 https://doaj.org/article/16603bd40eef4479946621b142ce0307 https://www.mdpi.com/2076-3417/13/3/1841 https://doaj.org/toc/2076-3417
remote_bool	true
author2	Sanghun Lee Hyunho Han
author2Str	Sanghun Lee Hyunho Han
ppnlink	737287640
callnumber-subject	TA - General and Civil Engineering
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/app13031841
callnumber-a	TA1-2040
up_date	2024-07-03T16:01:11.761Z
_version_	1803574283350310912
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ080682839</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413070706.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/app13031841</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ080682839</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ16603bd40eef4479946621b142ce0307</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TA1-2040</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QH301-705.5</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QC1-999</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QD1-999</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Beomyeon Hwang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Recent advances in convolutional neural network (CNN)-based object detection have a trade-off between accuracy and computational cost in various industrial tasks and essential consideration. However, the fully convolutional one-stage detector (FCOS) demonstrates low accuracy compared with its computational costs owing to the loss of low-level information. Therefore, we propose a module called a dual-path lightweight module (DLM) that efficiently utilizes low-level information. In addition, we propose a DLMFCOS based on DLM to achieve an optimal trade-off between computational cost and detection accuracy. Our network minimizes feature loss by extracting spatial and channel information in parallel and implementing a bottom-up feature pyramid network that improves low-level information detection. Additionally, the structure of the detection head is improved to minimize the computational cost. The proposed method was trained and evaluated by fine-tuning parameters through experiments and using public datasets PASCAL VOC 07 and MS COCO 2017 datasets. The average precision (AP) metric is used for our quantitative evaluation matrix for detection performance, and our model achieves an average 1.5% accuracy improvement at about 33.85% lower computational cost on each dataset than the conventional method. Finally, the efficiency of the proposed method is verified by comparing the proposed method with the conventional method through an ablation study.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">dual-path lightweight module</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">fully convolutional one-stage object detector</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">feature pyramid</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Technology</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">T</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Engineering (General). Civil engineering (General)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Biology (General)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Physics</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Chemistry</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Sanghun Lee</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Hyunho Han</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Applied Sciences</subfield><subfield code="d">MDPI AG, 2012</subfield><subfield code="g">13(2023), 3, p 1841</subfield><subfield code="w">(DE-627)737287640</subfield><subfield code="w">(DE-600)2704225-X</subfield><subfield code="x">20763417</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:13</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:3, p 1841</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/app13031841</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/16603bd40eef4479946621b142ce0307</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2076-3417/13/3/1841</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2076-3417</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">13</subfield><subfield code="j">2023</subfield><subfield code="e">3, p 1841</subfield></datafield></record></collection>
score	7.400199

Nicht das Richtige dabei?

Schreiben Sie uns!

DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?