Tephritid26: A standardized, multi-angle image dataset of quarantine-significant true fruit flies for deep learning-based identification

Accurate and rapid identification of quarantine-significant tephritids is critical to global agricultural biosecurity, but the application of deep learning is limited by the lack of large public image datasets. We present Tephritid26, a multi-angle image dataset of 26 tephritid species to address this gap. The dataset includes 38,081 images from 1,473 specimens across seven genera and two subfamilies, assembled through a global collaborative effort to source these regulated species. Specimens were mounted using a novel protocol combining varied thoracic attachment points and pin angles, and a rotational imaging setup then systematically captured each specimen from multiple perspectives to mimic real inspection conditions. The dataset is formatted for machine learning workflows. To demonstrate its utility, we trained deep learning models for species identification. ResNet-50, ConvNeXt-B, Vit-Small and Swin-Tiny all attained high species-level accuracy (Macro-Averaged F1-score > 96.75). Gradient-weighted Class Activation Mapping confirmed that the models focused on taxonomically informative morphological regions. This dataset serves as a benchmark for developing automated identification tools in phytosanitary applications.

Authors

Institutions

Publication Details

Journal
Scientific Data
Published
2026-06-27
DOI
https://doi.org/10.1038/s41597-026-07713-2
Primary Topic
Insect behavior and control techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Tephritid26: A standardized, multi-angle image dataset of quarantine-significant true fruit flies for deep learning-based identification

X Wang, Z Y Li, Xuankun Li, Weiqi Liu et al.
Scientific Data
Insect behavior and control techniques
article

Tephritid26: A standardized, multi-angle image dataset of quarantine-significant true fruit flies for deep learning-based identification

X Wang, Z Y Li, Xuankun Li, Weiqi Liu, Xin Yu, Zhuojie Wu, X K HUANG, Liu R, Xinhua Ding, Tianyu Zheng, Jin Mo, Mengyuan Yong, Qian Zeng, Kostas Bourtzis, Ding Yang, Daifeng Cheng, Marc De Meyer, Fan Jiang, Agus Susanto, Wenchao Guo, Bingbing Wei
article en

Abstract

Accurate and rapid identification of quarantine-significant tephritids is critical to global agricultural biosecurity, but the application of deep learning is limited by the lack of large public image datasets. We present Tephritid26, a multi-angle image dataset of 26 tephritid species to address this gap. The dataset includes 38,081 images from 1,473 specimens across seven genera and two subfamilies, assembled through a global collaborative effort to source these regulated species. Specimens were mounted using a novel protocol combining varied thoracic attachment points and pin angles, and a rotational imaging setup then systematically captured each specimen from multiple perspectives to mimic real inspection conditions. The dataset is formatted for machine learning workflows. To demonstrate its utility, we trained deep learning models for species identification. ResNet-50, ConvNeXt-B, Vit-Small and Swin-Tiny all attained high species-level accuracy (Macro-Averaged F1-score > 96.75). Gradient-weighted Class Activation Mapping confirmed that the models focused on taxonomically informative morphological regions. This dataset serves as a benchmark for developing automated identification tools in phytosanitary applications.

Scientific Data
South China Agricultural University (CN), International Atomic Energy Agency (AT), Royal Museum for Central Africa (BE), Mansfield University (US), The University of Queensland (AU), Huazhong Agricultural University (CN), Chinese Academy of Inspection and Quarantine (CN), Institute of Plant Protection (CN), Shanghai Customs College (CN), Ministry of Agriculture and Rural Affairs (CN), Institute of Quality Standards and Testing Technology for Agro Products (CN), China Agricultural University (CN), Changsha University of Science and Technology (CN), Fujian Agriculture and Forestry University (CN), Padjadjaran University (ID)
University of Memphis, National Natural Science Foundation of China, China Agricultural University, Huazhong Agricultural University
Zero hunger
Openalex Percentile: Top 7%
Insect behavior and control techniques
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.