Scarfnet: Multi-scale features with deeply fused and redistributed semantics for enhanced object detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoo, Jin Hyeok | - |
dc.contributor.author | Kum, Dongsuk | - |
dc.contributor.author | Choi, Jun Won | - |
dc.date.accessioned | 2022-07-07T01:20:13Z | - |
dc.date.available | 2022-07-07T01:20:13Z | - |
dc.date.created | 2021-11-22 | - |
dc.date.issued | 2021-01 | - |
dc.identifier.issn | 1051-4651 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/142433 | - |
dc.description.abstract | Convolutional neural networks (CNNs) have led us to achieve significant progress in object detection research. To detect objects of various sizes, object detectors often exploit the hierarchy of the multiscale feature maps called feature pyramids, which are readily obtained by the CNN architecture. However, the performance of these object detectors is limited because the bottom-level feature maps, which experience fewer convolutional layers, lack the semantic information needed to capture the characteristics of the small objects. To address such problems, various methods have been proposed to increase the depth for the bottom-level features used for object detection. While most approaches are based on the generation of additional features through the top-down pathway with lateral connections, our approach directly fuses multi-scale feature maps using bidirectional long short-term memory (biLSTM) in an effort to leverage the gating functions and parameter-sharing in generating deeply fused semantics. The resulting semantic information is redistributed to the individual pyramidal feature at each scale through the channel-wise attention model. We integrate our semantic combining and attentive redistribution feature network (ScarfNet) with the baseline object detectors, i.e., Faster R-CNN, single-shot multibox detector (SSD), and RetinaNet. Experimental results show that our method offers a significant performance gain over the baseline detectors and outperforms the competing multiscale fusion methods in the PASCAL VOC and COCO detection benchmarks. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Scarfnet: Multi-scale features with deeply fused and redistributed semantics for enhanced object detection | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Choi, Jun Won | - |
dc.identifier.doi | 10.1109/ICPR48806.2021.9412795 | - |
dc.identifier.scopusid | 2-s2.0-85110507159 | - |
dc.identifier.bibliographicCitation | Proceedings - International Conference on Pattern Recognition, pp.4505 - 4512 | - |
dc.relation.isPartOf | Proceedings - International Conference on Pattern Recognition | - |
dc.citation.title | Proceedings - International Conference on Pattern Recognition | - |
dc.citation.startPage | 4505 | - |
dc.citation.endPage | 4512 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Benchmarking | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Feature extraction | - |
dc.subject.keywordPlus | Object recognition | - |
dc.subject.keywordPlus | Semantics | - |
dc.subject.keywordPlus | Gating functions | - |
dc.subject.keywordPlus | Lateral connections | - |
dc.subject.keywordPlus | Multi-scale features | - |
dc.subject.keywordPlus | Multiscale fusion | - |
dc.subject.keywordPlus | Object detectors | - |
dc.subject.keywordPlus | Parameter sharing | - |
dc.subject.keywordPlus | Performance Gain | - |
dc.subject.keywordPlus | Semantic information | - |
dc.subject.keywordPlus | Object detection | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9412795 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.