A semi-supervised approach for classifying insect developmental phases from repurposed IP102

Fatin Faiaz Ahsan; Melissa L. Thomas; Hamid Laga; Ferdous Sohel

doi:10.1016/j.compag.2025.111337

Back

A semi-supervised approach for classifying insect developmental phases from repurposed IP102

Journal article

Open access

Peer reviewed

A semi-supervised approach for classifying insect developmental phases from repurposed IP102

Fatin Faiaz Ahsan, Melissa L. Thomas, Hamid Laga and Ferdous Sohel

Computers and electronics in agriculture, Vol.242, 111337

2026

DOI: https://doi.org/10.1016/j.compag.2025.111337

Files and links (1)

pdf

Published 2.41 MBDownload View

Published (Version of Record)CC BY-NC V4.0, Open Access

Abstract

Insect pest classification

Insect life-stage

And semi-supervised learning

Identifying insect pests, whether as adults, larvae, or eggs, is critical in pest management. Computational learning algorithms have demonstrated strong potential in achieving high identification performance, but these methods typically require large, balanced, and well-annotated datasets. This creates a challenge for insect pest identification, as rare species, despite often being the most damaging to crops, are underrepresented in available datasets. Moreover, annotating large-scale datasets is both costly and labour-intensive. To address this issue, we develop a semi-supervised learning approach, Cost-Focal FixMatch, which extends the widely used FixMatch framework by integrating class-aware reweighting and focal loss to better handle class imbalance. Specifically, we introduce a simple yet robust method for applying class weighting in cross-entropy and focal loss functions. The proposed method generates higher-quality pseudo labels compared to the baseline, ensuring better learning. We evaluate our approach using a repurposed IP102 dataset, which comprises four primary insect life stages, and a mixed IP102 dataset, where the class labels jointly represent insect species and their corresponding life stages. Our method considerably improves the classification of minority classes, achieving a notable increase in recall for the Larva class from 64% under the baseline FixMatch to 82% using MobileNetV3Small backbone. On the Mixed IP102 dataset, our approach achieves almost 9% better improved average recall than the baseline FixMatch built upon the EfficientNetV2S network.

Details

Title: A semi-supervised approach for classifying insect developmental phases from repurposed IP102
Authors/Creators: Fatin Faiaz Ahsan - Murdoch Univ, Sch Informat Technol, 90 South St, Murdoch, WA 6150, Australia
Melissa L. Thomas - Murdoch University
Hamid Laga - Murdoch Univ, Sch Informat Technol, 90 South St, Murdoch, WA 6150, Australia
Ferdous Sohel - Murdoch Univ, Sch Informat Technol, 90 South St, Murdoch, WA 6150, Australia
Publication Details: Computers and electronics in agriculture, Vol.242, 111337
Publisher: Elsevier
Number of pages: 14
Grant note: Australian Government Research Training Program (RTP) Scholarship; Australian Government; Department of Industry, Innovation and Science
Identifiers: 991005841254907891
Murdoch Affiliation: Centre for Biosecurity and One Health; School of Information Technology; Centre for Healthy Ageing
Language: English
Resource Type: Journal article

Metrics

1 File views/ downloads

6 Record Views

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Citation topics: 7 Engineering & Materials Science; 7.226 Electrical - Sensors & Monitoring; 7.226.2419 Ultrasonic Flow Measurement
Web Of Science research areas: Agriculture, Multidisciplinary; Computer Science, Interdisciplinary Applications
ESI research areas: Computer Science