Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 문영식 | - |
dc.date.accessioned | 2023-08-21T06:37:03Z | - |
dc.date.available | 2023-08-21T06:37:03Z | - |
dc.date.issued | 2020-12 | - |
dc.identifier.citation | 2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020, article no. 9345302, Page. 1224-1228 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/9345302 | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/185519 | - |
dc.description.abstract | In recent years, object detectors generally use the feature pyramid network (FPN) to solve the problem of scale variation in object detection. In this paper, we propose a new architecture of feature pyramid network which combines a top-down feature pyramid network and a bottom-up feature pyramid network. The main contributions of the proposed method are two-fold: (1) We design a more complex feature pyramid network to get the feature maps for object detection. (2) By combining these two architectures, we can get the feature maps with richer semantic information to solve the problem of scale variation better. The proposed method experiments on PASCAL VOC2007 dataset. Experimental results show that the proposed method can improve the accuracy of detectors using the FPN by about 1.67%. © 2020 IEEE. | - |
dc.language | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.subject | deep learning | - |
dc.subject | feature pyramid network | - |
dc.subject | object detection | - |
dc.subject | RetinaNet | - |
dc.title | A New Architecture of Feature Pyramid Network for Object Detection | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICCC51575.2020.9345302 | - |
dc.relation.page | 1224-1228 | - |
dc.relation.journal | 2020 IEEE 6th International Conference on Computer and Communications, ICCC 2020 | - |
dc.contributor.googleauthor | Zhang, Yichen | - |
dc.contributor.googleauthor | Han, Jeong hoon | - |
dc.contributor.googleauthor | Kwon, Yong woo | - |
dc.contributor.googleauthor | Moon, Young shik | - |
dc.sector.campus | E | - |
dc.sector.daehak | 소프트웨어융합대학 | - |
dc.sector.department | 소프트웨어학부 | - |
dc.identifier.pid | ysmoon | - |
dc.identifier.article | 9345302 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.