Deep-Wide Learning Assistance for Insect Pest Classification

Toan Nguyen, Huy Nguyen, Huy Ung, Hieu Ung, Binh Nguyen
9/16/2024
cs.CV

Official code: toannguyen1904/DeWi (10 stars, last commit 2024-07-17).

Abstract

Accurate insect pest recognition plays a critical role in agriculture. It is a challenging problem due to the intricate characteristics of insects. In this paper, we present DeWi, novel learning assistance for insect pest classification. With a one-stage and alternating training strategy, DeWi simultaneously improves several Convolutional Neural Networks in two perspectives: discrimination (by optimizing a triplet margin loss in a supervised training manner) and generalization (via data augmentation). From that, DeWi can learn discriminative and in-depth features of insect pests (deep) yet still generalize well to a large number of insect categories (wide). Experimental results show that DeWi achieves the highest performances on two insect pest classification benchmarks (76.44\% accuracy on the IP102 dataset and 99.79\% accuracy on the D0 dataset, respectively). In addition, extensive evaluations and ablation studies are conducted to thoroughly investigate our DeWi and demonstrate its superiority. Our source code is available at https://github.com/toannguyen1904/DeWi.

View on arXivView PDF

Code Implementations(1)

toannguyen1904/DeWiOfficial100%

Official code of the paper "Deep-Wide Learning Assistance for Insect Pest Classification"

100PythonOct 15, 20232 years ago
computer-visionconvolutional-neural-networkinsect-classificationmachine-learningneural-network+1 more

Similar Papers

InsectMamba: Insect Pest Classification with State Space Model

91% match2024

Unleashing the Power of Transfer Learning Model for Sophisticated Insect Detection: Revolutionizing Insect Classification

86% match2024

BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data

86% match2025

Crop Pest Classification Using Deep Learning Techniques: A Review

85% match2025

Investigation to answer three key questions concerning plant pest identification and development of a practical identification framework

83% match2024

Self-supervised transformer-based pre-training method with General Plant Infection dataset

83% match2024

Cite this paper

@article{nguyen2024deepwide,
  title  = {Deep-Wide Learning Assistance for Insect Pest Classification},
  author = {Toan Nguyen and Huy Nguyen and Huy Ung and Hieu Ung and Binh Nguyen},
  year   = {2024},
  eprint = {2409.10445},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.10445v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.10445.svg)](https://codeofpaper.com/paper/2409.10445)

Discussion