Spatial reasoning for few-shot object detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Geonuk | - |
dc.contributor.author | Jung, Hong-Gyu | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2022-02-12T21:40:44Z | - |
dc.date.available | 2022-02-12T21:40:44Z | - |
dc.date.created | 2022-02-09 | - |
dc.date.issued | 2021-12 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/135547 | - |
dc.description.abstract | Although modern object detectors rely heavily on a significant amount of training data, humans can eas-ily detect novel objects using a few training examples. The mechanism of the human visual system is to interpret spatial relationships among various objects and this process enables us to exploit contextual information by considering the co-occurrence of objects. Thus, we propose a spatial reasoning framework that detects novel objects with only a few training examples in a context. We infer geometric related-ness between novel and base RoIs (Region-of-Interests) to enhance the feature representation of novel categories using an object detector well trained on base categories. We employ a graph convolutional network as the RoIs and their relatedness are defined as nodes and edges, respectively. Furthermore, we present spatial data augmentation to overcome the few-shot environment where all objects and bounding boxes in an image are resized randomly. Using the PASCAL VOC and MS COCO datasets, we demonstrate that the proposed method significantly outperforms the state-of-the-art methods and verify its efficacy through extensive ablation studies. (c) 2021 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.title | Spatial reasoning for few-shot object detection | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1016/j.patcog.2021.108118 | - |
dc.identifier.scopusid | 2-s2.0-85108947213 | - |
dc.identifier.wosid | 000691542900009 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.120 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 120 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordAuthor | Data augmentation | - |
dc.subject.keywordAuthor | Few-shot learning | - |
dc.subject.keywordAuthor | Object detection | - |
dc.subject.keywordAuthor | Transfer learning | - |
dc.subject.keywordAuthor | Visual reasoning | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
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.