Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318778262> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4318778262 endingPage "1841" @default.
- W4318778262 startingPage "1841" @default.
- W4318778262 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." @default.
- W4318778262 created "2023-02-02" @default.
- W4318778262 creator A5009750769 @default.
- W4318778262 creator A5037681735 @default.
- W4318778262 creator A5071856047 @default.
- W4318778262 date "2023-01-31" @default.
- W4318778262 modified "2023-10-18" @default.
- W4318778262 title "DLMFCOS: Efficient Dual-Path Lightweight Module for Fully Convolutional Object Detection" @default.
- W4318778262 cites W1536680647 @default.
- W4318778262 cites W1861492603 @default.
- W4318778262 cites W1903029394 @default.
- W4318778262 cites W2031489346 @default.
- W4318778262 cites W2117539524 @default.
- W4318778262 cites W2194775991 @default.
- W4318778262 cites W2288122362 @default.
- W4318778262 cites W2531409750 @default.
- W4318778262 cites W2565639579 @default.
- W4318778262 cites W2570343428 @default.
- W4318778262 cites W2752782242 @default.
- W4318778262 cites W2884585870 @default.
- W4318778262 cites W2960387718 @default.
- W4318778262 cites W2962721361 @default.
- W4318778262 cites W2962766617 @default.
- W4318778262 cites W2962992847 @default.
- W4318778262 cites W2963037989 @default.
- W4318778262 cites W2963068995 @default.
- W4318778262 cites W2963150697 @default.
- W4318778262 cites W2963163009 @default.
- W4318778262 cites W2963299996 @default.
- W4318778262 cites W2963351448 @default.
- W4318778262 cites W2963372104 @default.
- W4318778262 cites W2963516811 @default.
- W4318778262 cites W2963857746 @default.
- W4318778262 cites W2982770724 @default.
- W4318778262 cites W2999309192 @default.
- W4318778262 cites W3014641072 @default.
- W4318778262 cites W3102701618 @default.
- W4318778262 cites W3106250896 @default.
- W4318778262 cites W3199835541 @default.
- W4318778262 cites W3201722512 @default.
- W4318778262 cites W4285290430 @default.
- W4318778262 cites W4294833963 @default.
- W4318778262 cites W4295220592 @default.
- W4318778262 cites W4308237512 @default.
- W4318778262 cites W639708223 @default.
- W4318778262 doi "https://doi.org/10.3390/app13031841" @default.
- W4318778262 hasPublicationYear "2023" @default.
- W4318778262 type Work @default.
- W4318778262 citedByCount "2" @default.
- W4318778262 countsByYear W43187782622023 @default.
- W4318778262 crossrefType "journal-article" @default.
- W4318778262 hasAuthorship W4318778262A5009750769 @default.
- W4318778262 hasAuthorship W4318778262A5037681735 @default.
- W4318778262 hasAuthorship W4318778262A5071856047 @default.
- W4318778262 hasBestOaLocation W43187782621 @default.
- W4318778262 hasConcept C11413529 @default.
- W4318778262 hasConcept C138885662 @default.
- W4318778262 hasConcept C153180895 @default.
- W4318778262 hasConcept C154945302 @default.
- W4318778262 hasConcept C179799912 @default.
- W4318778262 hasConcept C199360897 @default.
- W4318778262 hasConcept C2776151529 @default.
- W4318778262 hasConcept C2776401178 @default.
- W4318778262 hasConcept C41008148 @default.
- W4318778262 hasConcept C41895202 @default.
- W4318778262 hasConcept C75608658 @default.
- W4318778262 hasConcept C81363708 @default.
- W4318778262 hasConceptScore W4318778262C11413529 @default.
- W4318778262 hasConceptScore W4318778262C138885662 @default.
- W4318778262 hasConceptScore W4318778262C153180895 @default.
- W4318778262 hasConceptScore W4318778262C154945302 @default.
- W4318778262 hasConceptScore W4318778262C179799912 @default.
- W4318778262 hasConceptScore W4318778262C199360897 @default.
- W4318778262 hasConceptScore W4318778262C2776151529 @default.
- W4318778262 hasConceptScore W4318778262C2776401178 @default.
- W4318778262 hasConceptScore W4318778262C41008148 @default.
- W4318778262 hasConceptScore W4318778262C41895202 @default.
- W4318778262 hasConceptScore W4318778262C75608658 @default.
- W4318778262 hasConceptScore W4318778262C81363708 @default.
- W4318778262 hasIssue "3" @default.
- W4318778262 hasLocation W43187782621 @default.
- W4318778262 hasOpenAccess W4318778262 @default.
- W4318778262 hasPrimaryLocation W43187782621 @default.
- W4318778262 hasRelatedWork W2424871898 @default.
- W4318778262 hasRelatedWork W2767651786 @default.
- W4318778262 hasRelatedWork W2801801420 @default.
- W4318778262 hasRelatedWork W2912288872 @default.
- W4318778262 hasRelatedWork W2913302899 @default.
- W4318778262 hasRelatedWork W2952466432 @default.
- W4318778262 hasRelatedWork W3038672259 @default.
- W4318778262 hasRelatedWork W3135818718 @default.
- W4318778262 hasRelatedWork W4297914674 @default.
- W4318778262 hasRelatedWork W4318827001 @default.
- W4318778262 hasVolume "13" @default.
- W4318778262 isParatext "false" @default.
- W4318778262 isRetracted "false" @default.
- W4318778262 workType "article" @default.