WormNet: A Multi-View Network for Silkworm Re-Identification

Re-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individ...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongkang Shi, Minghui Zhu, Linbo Li, Yong Ma, Jianmei Wu, Jianfei Zhang, Junfeng Gao
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Animals
Subjects:
Online Access:https://www.mdpi.com/2076-2615/15/14/2011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067372753289216
author Hongkang Shi
Minghui Zhu
Linbo Li
Yong Ma
Jianmei Wu
Jianfei Zhang
Junfeng Gao
author_facet Hongkang Shi
Minghui Zhu
Linbo Li
Yong Ma
Jianmei Wu
Jianfei Zhang
Junfeng Gao
author_sort Hongkang Shi
collection DOAJ
description Re-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individuals, arbitrary poses, and significant background noise. To address these challenges, we propose a multi-view network for silkworm ReID, called WormNet, which is built upon an innovative strategy termed extraction purification extraction interaction. Specifically, we introduce a multi-order feature extraction module that captures a wide range of fine-grained features by utilizing convolutional kernels of varying sizes and parallel cardinality, effectively mitigating issues of high individual similarity and diverse poses. Next, a feature mask module (FMM) is employed to purify the features in the spatial domain, thereby reducing the impact of background interference. To further enhance the data representation capabilities of the network, we propose a channel interaction module (CIM), which combines an efficient channel attention network with global response normalization (GRN) in parallel to recalibrate features, enabling the network to learn crucial information at both the local and global scales. Additionally, we introduce a new silkworm ReID dataset for network training and evaluation. The experimental results demonstrate that WormNet achieves an mAP value of 54.8% and a rank-1 value of 91.4% on the dataset, surpassing both state-of-the-art and related networks. This study offers a valuable reference for ReID in insects and other organisms.
format Article
id doaj-art-dfa64faf0aef471e99ce312af40e8b75
institution DOAJ
issn 2076-2615
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Animals
spelling doaj-art-dfa64faf0aef471e99ce312af40e8b752025-08-20T02:48:19ZengMDPI AGAnimals2076-26152025-07-011514201110.3390/ani15142011WormNet: A Multi-View Network for Silkworm Re-IdentificationHongkang Shi0Minghui Zhu1Linbo Li2Yong Ma3Jianmei Wu4Jianfei Zhang5Junfeng Gao6Sericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaSericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaSericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaSericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaSericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaSericultural Research Institute, Sichuan Academy of Agricultural Sciences, Nanchong 637000, ChinaDepartment of Computer Science, University of Aberdeen, Aberdeen AB24 3FX, UKRe-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individuals, arbitrary poses, and significant background noise. To address these challenges, we propose a multi-view network for silkworm ReID, called WormNet, which is built upon an innovative strategy termed extraction purification extraction interaction. Specifically, we introduce a multi-order feature extraction module that captures a wide range of fine-grained features by utilizing convolutional kernels of varying sizes and parallel cardinality, effectively mitigating issues of high individual similarity and diverse poses. Next, a feature mask module (FMM) is employed to purify the features in the spatial domain, thereby reducing the impact of background interference. To further enhance the data representation capabilities of the network, we propose a channel interaction module (CIM), which combines an efficient channel attention network with global response normalization (GRN) in parallel to recalibrate features, enabling the network to learn crucial information at both the local and global scales. Additionally, we introduce a new silkworm ReID dataset for network training and evaluation. The experimental results demonstrate that WormNet achieves an mAP value of 54.8% and a rank-1 value of 91.4% on the dataset, surpassing both state-of-the-art and related networks. This study offers a valuable reference for ReID in insects and other organisms.https://www.mdpi.com/2076-2615/15/14/2011insect re-identificationmulti-order extractionchannel interactionspatial purificationsilkworm
spellingShingle Hongkang Shi
Minghui Zhu
Linbo Li
Yong Ma
Jianmei Wu
Jianfei Zhang
Junfeng Gao
WormNet: A Multi-View Network for Silkworm Re-Identification
Animals
insect re-identification
multi-order extraction
channel interaction
spatial purification
silkworm
title WormNet: A Multi-View Network for Silkworm Re-Identification
title_full WormNet: A Multi-View Network for Silkworm Re-Identification
title_fullStr WormNet: A Multi-View Network for Silkworm Re-Identification
title_full_unstemmed WormNet: A Multi-View Network for Silkworm Re-Identification
title_short WormNet: A Multi-View Network for Silkworm Re-Identification
title_sort wormnet a multi view network for silkworm re identification
topic insect re-identification
multi-order extraction
channel interaction
spatial purification
silkworm
url https://www.mdpi.com/2076-2615/15/14/2011
work_keys_str_mv AT hongkangshi wormnetamultiviewnetworkforsilkwormreidentification
AT minghuizhu wormnetamultiviewnetworkforsilkwormreidentification
AT linboli wormnetamultiviewnetworkforsilkwormreidentification
AT yongma wormnetamultiviewnetworkforsilkwormreidentification
AT jianmeiwu wormnetamultiviewnetworkforsilkwormreidentification
AT jianfeizhang wormnetamultiviewnetworkforsilkwormreidentification
AT junfenggao wormnetamultiviewnetworkforsilkwormreidentification