Publications

Detailed Information

Few-Shot Object Detection by Attending to Per-Sample-Prototype

DC Field Value Language
dc.contributor.authorLee, Hojun-
dc.contributor.authorLee, Myunggi-
dc.contributor.authorKwak, Nojun-
dc.date.accessioned2024-08-08T01:22:51Z-
dc.date.available2024-08-08T01:22:51Z-
dc.date.created2022-05-09-
dc.date.created2022-05-09-
dc.date.issued2022-01-
dc.identifier.citationProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022, pp.1101-1110-
dc.identifier.issn2472-6737-
dc.identifier.urihttps://hdl.handle.net/10371/205538-
dc.description.abstract© 2022 IEEE.Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised object detection, it results in a far inferior performance compared to the conventional object detection methods. In this paper, we propose a meta-learning-based approach that con-siders the unique characteristics of each support sample. Rather than simply averaging the information of the support samples to generate a single prototype per category, our method can better utilize the information of each support sample by treating each support sample as an individual prototype. Specifically, we introduce two types of attention mechanisms for aggregating the query and support feature maps. The first is to refine the information of few-shot samples by extracting shared information between the support samples through attention. Second, each support sample is used as a class code to leverage the information by comparing similarities between each support feature and query features. Our proposed method is complementary to the previous methods, making it easy to plug and play for further improvement. We have evaluated our method on PASCAL VOC and COCO benchmarks, and the results verify the effectiveness of our method. In particular, the advantages of our method are maximized when there is more diversity among support data.-
dc.language영어-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.titleFew-Shot Object Detection by Attending to Per-Sample-Prototype-
dc.typeArticle-
dc.identifier.doi10.1109/WACV51458.2022.00117-
dc.citation.journaltitleProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022-
dc.identifier.wosid000800471201016-
dc.identifier.scopusid2-s2.0-85126140560-
dc.citation.endpage1110-
dc.citation.startpage1101-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorKwak, Nojun-
dc.type.docTypeProceedings Paper-
dc.description.journalClass1-
dc.subject.keywordAuthorFew-shot-
dc.subject.keywordAuthorSemi- and Un- supervised Learning Object Detection/Recognition/Categorization-
dc.subject.keywordAuthorTransfer-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • Graduate School of Convergence Science & Technology
  • Department of Intelligence and Information
Research Area Feature Selection and Extraction, Object Detection, Object Recognition

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share