Show simple item record

Multi-Scale Cross-Domain Augmentation of Tea Datasets via Enhanced Cycle Adversarial Networks

dc.contributor.authorTaojie Yu
dc.contributor.authorJianneng Chen
dc.contributor.authorZhiyong Gui
dc.contributor.authorJiangming Jia
dc.contributor.authorYatao Li
dc.contributor.authorChennan Yu
dc.contributor.authorChuanyu Wu
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherSchool of Mechanical Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China
dc.contributor.otherZhejiang Ocean University, Zhoushan 316022, China
dc.date.accessioned2025-08-27T14:00:13Z
dc.date.accessioned2025-10-08T09:00:43Z
dc.date.available2025-10-08T09:00:43Z
dc.date.issued01-08-2025
dc.identifier.urihttp://digilib.fisipol.ugm.ac.id/repo/handle/15717717/38588
dc.description.abstractTo tackle phenotypic variability and detection accuracy issues of tea shoots in open-air gardens due to lighting and varietal differences, this study proposes Tea CycleGAN and a data augmentation method. It combines multi-scale image style transfer with spatial consistency dataset generation. Using Longjing 43 and Zhongcha 108 as cross-domain objects, the generator integrates SKConv and a dynamic multi-branch residual structure for multi-scale feature fusion, optimized by an attention mechanism. A deep discriminator with more conv layers and batch norm enhances detail discrimination. A global–local framework trains on 600 × 600 background and 64 × 64 tea shoots regions, with a restoration-paste strategy to preserve spatial consistency. Experiments show Tea CycleGAN achieves <i>FID</i> scores of 42.26 and 26.75, outperforming CycleGAN. Detection using YOLOv7 sees <i>mAP</i> rise from 73.94% to 83.54%, surpassing Mosaic and Mixup. The method effectively mitigates lighting/scale impacts, offering a reliable data augmentation solution for tea picking.
dc.language.isoEN
dc.publisherMDPI AG
dc.subject.lccAgriculture (General)
dc.titleMulti-Scale Cross-Domain Augmentation of Tea Datasets via Enhanced Cycle Adversarial Networks
dc.typeArticle
dc.description.keywordsCycleGAN
dc.description.keywordstea shoots
dc.description.keywordsdata augmentation
dc.description.keywordsstyle transfer
dc.description.keywordsmulti-scale feature
dc.description.doi10.3390/agriculture15161739
dc.title.journalAgriculture
dc.identifier.e-issn2077-0472
dc.identifier.oaioai:doaj.org/journal:15a268b0fb7b4de6a8686252d60b4fbc
dc.journal.infoVolume 15, Issue 16


This item appears in the following Collection(s)

Show simple item record