research-article

Rectified Meta-learning from Noisy Labels for Robust Image-based Plant Disease Classification

Authors:

Xianming LiuAuthors Info & Claims

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 18, Issue 1s

Article No.: 30, Pages 1 - 17

https://doi.org/10.1145/3472809

Published: 25 January 2022 Publication History

Abstract

Plant diseases serve as one of main threats to food security and crop production. It is thus valuable to exploit recent advances of artificial intelligence to assist plant disease diagnosis. One popular approach is to transform this problem as a leaf image classification task, which can be then addressed by the powerful convolutional neural networks (CNNs). However, the performance of CNN-based classification approach depends on a large amount of high-quality manually labeled training data, which inevitably introduce noise on labels in practice, leading to model overfitting and performance degradation. To overcome this problem, we propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information. The proposed method enjoys the following merits: (i) A rectified meta-learning is designed to pay more attention to unbiased samples, leading to accelerated convergence and improved classification accuracy. (ii) Our method is free on assumption of label noise distribution, which works well on various kinds of noise. (iii) Our method serves as a plug-and-play module, which can be embedded into any deep models optimized by gradient descent-based method. Extensive experiments are conducted to demonstrate the superior performance of our algorithm over the state-of-the-arts.

References

[1]

Matthew Botvinick, Daan Wierstra, Adam Santoro, Sergey Bartunov, and Timothy Lillicrap. 2016. Metalearning with memory-augmented neural networks. In IEEE International Conference on Machine Learning.

Digital Library

[2]

Misha Denil, Sergio Gomez Colmenarejo, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Marcin Andrychowicz, and Nando De Freitas. 2016. Learning to learn by gradient descent by gradient descent. In Conference on Advances in Neural Information Processing Systems.

Digital Library

[3]

Jayme G. A. Barbedo. 2018. Factors influencing the use of deep learning for plant disease recognition. Biosyst. Eng. 172 (2018), 84–91.

[4]

Richard N. Strange and Peter R. Scott. 2005. Plant disease: A threat to global food security. Ann. Rev. Phytopathol. 43, 1 (2005), 83–116.

[5]

Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Matt Botvinick, and Nando de Freitas. 2017. Learning to learn without gradient descent by gradient descent. Proc. Mach. Learn. Res. 70 (2017), 748–756.

Digital Library

[6]

ChristianeLemke, MarcinBudka, and BogdanGabrys. 2015. Metalearning: A survey of trends and technologies. Artif. Intell. Rev. 44, 1 (2015), 117–130.

Digital Library

[7]

Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. 2018. Using trusted data to train deep networks on labels corrupted by severe noise. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).

Digital Library

[8]

Dougal Maclaurin, David Duvenaud, and Ryan Adams. 2015. Gradient-based hyperparameter optimization through reversible learning. In 32nd International Conference on Machine Learning.

Digital Library

[9]

and Konstantinos P. Ferentinos.2018. Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agricult. 145 (2018), 311–318.

[10]

Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In IEEE International Conference on Machine Learning (ICML).

Digital Library

[11]

Wang Guan, Sun Yu, and Wang Jianxi. 2017. Automatic image-based plant disease severity estimation using deep learning. Comput. Intell. Neurosci. 2017 (2017), 1–8.

[12]

Jiangfan Han, Ping Luo, and Xiaogang Wang. 2019. Deep self-learning from noisy labels. In IEEE International Conference on Computer Vision (ICCV) (2019).

[13]

Celia A. Harvey, Zo Lalaina Rakotobe, Nalini S. Rao, Radhika Dave, and James L. Mackinnon. 2014. Extreme vulnerability of smallholder farmers to agricultural risks and climate change in madagascar. Philos. Trans. Roy. Societ. Lond. 369, 1639 (2014), 20130089.

[14]

Younger A. Steven, Hochreiter Sepp, and Peter R. Conwell. 2001. Learning to learn using gradient descent. In International Conference on Artificial Neural Networks.

Digital Library

[15]

David. P. Hughes and Marcel Salathe. 2015. An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing. Comput. Sci. (2015).

[16]

Goldberger Jacob and Ben-Reuven Ehud. 2016. Training deep neural-networks using a noise adaptation layer. In IEEE International Conference on Learning Representations (ICLR).

[17]

Kevin Swersky, Jake Snell, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).

Digital Library

[18]

Rajleen Kaur and Sandeep Singh Kang. 2016. An enhancement in classifier support vector machine to improve plant disease detection. In IEEE International Conference on MOOCs, Innovation and Technology in Education. 135–140.

[19]

Sachin D. Khirade and A. B. Patil. 2015. Plant disease detection using image processing. In International Conference on Computing Communication Control and Automation. IEEE Computer Society.

Digital Library

[20]

Youngdong Kim, Junho Yim, Juseung Yun, and Junmo Kim. 2019. NLNL: Negative learning for noisy labels. In IEEE/CVF International Conference on Computer Vision (ICCV). 101–110.

[21]

Alex Krizhevsky and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. Master’s Thesis. University of Toronto.

[22]

M. Pawan Kumar, Benjamin Packer, and Daphne Koller. 2010. Self-paced learning for latent variable models. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).

Digital Library

[23]

Kuang-Huei Lee, Xiaodong He, Lei Zhang, and Linjun Yang. 2018. CleanNet: Transfer learning for scalable image classifier training with label noise. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]

Junnan Li, Yongkang Wong, Qi Zhao, and Mohan Kankanhalli. 2019. Learning to learn from noisy labeled data. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5051–5059.

[25]

Niu Li, Qingtao Tang, Ashok Veeraraghavan, and Ashu Sabharwal. 2018. Learning from noisy web data with category level supervision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]

Yuncheng Li, Jianchao Yang, Yale Song, Liangliang Cao, Jiebo Luo, and Li Jia Li. 2017. Learning from noisy labels with distillation. In IEEE International Conference on Computer Vision (ICCV). 1928–1936.

[27]

Tsung Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. PP, 99 (2017), 2999–3007.

[28]

Xin Liu, Shaoxin Li, Meina Kan, Shiguang Shan, and Xilin Chen. 2017. Self-error-correcting convolutional neural network for learning with noisy labels. In 12th IEEE International Conference on Automatic Face Gesture Recognition (FG’17). 111–117.

[29]

Tomasz Malisiewicz, Abhinav Gupta, and Alexei A. Efros. 2011. Ensemble of exemplar-SVMs for object detection and beyond. In IEEE International Conference on Computer Vision (ICCV).

Digital Library

[30]

Sharada P. Mohanty, David P. Hughes, and Marcel Salathé. 2016. Using deep learning for image-based plant disease detection. Front. Plant Sci. 7 (2016), 1419.

[31]

Timothy Lillicrap, Daan Wierstra, Oriol Vinyals, Charles Blundell, et al. 2016. Matching networks for one shot learning. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).

Digital Library

[32]

Giorgio Patrini, Alessandro Rozza, Aditya Menon, Richard Nock, and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1944–1952.

[33]

Scott, Honglak E. Reed, Dragomir Lee, Christian Anguelov, Dumitru Szegedy, Erhan, and Andrew Rabinovich. 2015. Training deep convolutional networks on noisy labels with bootstrapping. In IEEE International Conference on Learning Representations (ICLR).

[34]

Guo Sheng, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, and Dinglong Huang. 2018. CurriculumNet: Weakly supervised learning from large-scale web images. In European Conference on Computer Vision.

[35]

Sainbayar Sukhbaatar, Joan Bruna, Manohar Paluri, Lubomir Bourdev, and Rob Fergus. 2014. Training convolutional networks with noisy labels. In IEEE International Conference on Learning Representations (ICLR).

[36]

Daiki Tanaka, Daiki Ikami, Toshihiko Yamasaki, and Kiyoharu Aizawa. 2018. Joint optimization framework for learning with noisy labels. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5552–5560.

[37]

Andreas Veit, Neil Alldrin, Gal Chechik, Ivan Krasin, Abhinav Gupta, and Serge Belongie. 2017. Learning from noisy large-scale datasets with minimal supervision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]

Ricardo Vilalta and Youssef Drissi. 2001. A perspective view and survey of meta-learning. Artif. Intell. Rev. 18, 2 (2001).

Digital Library

[39]

Harshal Waghmare, Radha Kokare, and Yogesh Dandawate. 2016. Detection and classification of diseases of grape plant using opposite colour local binary pattern feature and machine learning for automated decision support system. In International Conference on Signal Processing and Integrated Networks. IEEE.

[40]

Kurth-Nelson, Zeb Tirumala, Dhruva Soyer, Hubert Leibo, Joel Z. Munos, Rémi Blundell, Charles Kumaran, Dharshan Wang, Jane X., and Matthew Botvinick. 2016. Learning to reinforcement learn. In Annual Meeting of the Cognitive Science Society.

[41]

Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, and Shu-Tao Xia. 2018. Iterative learning with open-set noisy labels. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8688–8696.

[42]

Yisen Wang, Xingjun Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, and James Bailey. 2019. Symmetric cross entropy for robust learning with noisy labels. In IEEE International Conference on Computer Vision.

[43]

Wang Xiaobo, Wang Shuo, Wang Jun, Shi Hailin, and Mei Tao. 2019. Co-mining: Deep face recognition with noisy labels. In IEEE International Conference on Computer Vision (ICCV).

[44]

Kun Yi and Jianxin Wu. 2019. Probabilistic end-to-end noise correction for learning with noisy labels. CoRR (2019). arxiv:1903.07788.

[45]

Zhilu Zhang and Mert R. Sabuncu. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).

[46]

Fei Chen Zhenguo Li, Fengwei Zhou, and Hang Li. 2017. Meta-SGD: Learning to learn quickly for few shot learning. arXiv:1707.09835 (2017).

Cited By

Wang SZeng QYuan GNi WLi CDuan HXie NXiao FYang X(2025)Generalized zero-shot pest and disease image classification based on causal gating modelComputers and Electronics in Agriculture10.1016/j.compag.2024.109827230(109827)Online publication date: Mar-2025
https://doi.org/10.1016/j.compag.2024.109827
Liang CZhu LYang ZChen WYang Y(2024)Noise-Tolerant Hybrid Prototypical Learning with Noisy Web DataACM Transactions on Multimedia Computing, Communications, and Applications10.1145/367239620:10(1-19)Online publication date: 8-Jul-2024
https://dl.acm.org/doi/10.1145/3672396
Antwi KBennin KPobi DTekinerdogan B(2024)On the application of Image augmentation for Plant Disease Detection: A Systematic Literature ReviewSmart Agricultural Technology10.1016/j.atech.2024.100590(100590)Online publication date: Oct-2024
https://doi.org/10.1016/j.atech.2024.100590
Show More Cited By

Index Terms

Rectified Meta-learning from Noisy Labels for Robust Image-based Plant Disease Classification
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Embedded systems
2. Computing methodologies
  1. Machine learning
    1. Learning settings
      1. Batch learning

Recommendations

How to handle noisy labels for robust learning from uncertainty
Abstract
Most deep neural networks (DNNs) are trained with large amounts of noisy labels when they are applied. As DNNs have the high capacity to fit any noisy labels, it is known to be difficult to train DNNs robustly with noisy labels. These ...
Collaborative Learning with Pseudo Labels for Robust Classification in the Presence of Noisy Labels
Computer Vision – ECCV 2020 Workshops
Abstract
Supervised learning depends on labels of dataset to train models with desired properties. Therefore, data containing mislabeled samples (a.k.a. noisy labels) can deteriorate supervised learning performance significantly as it makes models to be ...
Zero-Shot Learning with Noisy Labels
Abstract
Zero-shot learning (ZSL) is an attractive technique that can recognize novel object classes without any visual examples, but most existing methods assume that the class labels of the training instances from seen classes are accurate and reliable. ...

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Multimedia Computing, Communications, and Applications

ACM Transactions on Multimedia Computing, Communications, and Applications Volume 18, Issue 1s

February 2022

352 pages

ISSN:1551-6857

EISSN:1551-6865

DOI:10.1145/3505206

Editor:
Alberto Del Bimbo
University of Firenze, Italy

Issue’s Table of Contents

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 January 2022

Accepted: 01 June 2021

Revised: 01 May 2021

Received: 01 January 2021

Published in TOMM Volume 18, Issue 1s

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Refereed

Funding Sources

Natural Science Foundation of China
China Postdoctoral Science Foundation

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
454
Total Downloads

Downloads (Last 12 months)46
Downloads (Last 6 weeks)0

Reflects downloads up to 27 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wang SZeng QYuan GNi WLi CDuan HXie NXiao FYang X(2025)Generalized zero-shot pest and disease image classification based on causal gating modelComputers and Electronics in Agriculture10.1016/j.compag.2024.109827230(109827)Online publication date: Mar-2025
https://doi.org/10.1016/j.compag.2024.109827
Liang CZhu LYang ZChen WYang Y(2024)Noise-Tolerant Hybrid Prototypical Learning with Noisy Web DataACM Transactions on Multimedia Computing, Communications, and Applications10.1145/367239620:10(1-19)Online publication date: 8-Jul-2024
https://dl.acm.org/doi/10.1145/3672396
Antwi KBennin KPobi DTekinerdogan B(2024)On the application of Image augmentation for Plant Disease Detection: A Systematic Literature ReviewSmart Agricultural Technology10.1016/j.atech.2024.100590(100590)Online publication date: Oct-2024
https://doi.org/10.1016/j.atech.2024.100590
Sanida TDasygenis M(2024)MiniTomatoNet: a lightweight CNN for tomato leaf disease recognition on heterogeneous FPGA-SoCThe Journal of Supercomputing10.1007/s11227-024-06301-880:15(21837-21866)Online publication date: 1-Oct-2024
https://dl.acm.org/doi/10.1007/s11227-024-06301-8
Xu MKim HYang JFuentes AMeng YYoon SKim TPark D(2023)Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learningFrontiers in Plant Science10.3389/fpls.2023.122540914Online publication date: 22-Sep-2023
https://doi.org/10.3389/fpls.2023.1225409
Gong WZhang YWang WCheng PGonzàlez J(2023)Meta-MMFNet: Meta-learning-based Multi-model Fusion Network for Micro-expression RecognitionACM Transactions on Multimedia Computing, Communications, and Applications10.1145/353957620:2(1-20)Online publication date: 25-Sep-2023
https://dl.acm.org/doi/10.1145/3539576
Wu XDeng HWang QLei LGao YHao G(2023)Meta‐learning shows great potential in plant disease recognition under few available samplesThe Plant Journal10.1111/tpj.16176114:4(767-782)Online publication date: 16-Apr-2023
https://doi.org/10.1111/tpj.16176
Alqahtani YNawaz MNazir TJaved AJeribi FTahir A(2023)An improved deep learning approach for localization and recognition of plant leaf diseasesExpert Systems with Applications10.1016/j.eswa.2023.120717230(120717)Online publication date: Nov-2023
https://doi.org/10.1016/j.eswa.2023.120717
Verma SKumar PSingh J(2023)A meta-learning framework for recommending CNN models for plant disease identification tasksComputers and Electronics in Agriculture10.1016/j.compag.2023.107708207:COnline publication date: 1-Apr-2023
https://dl.acm.org/doi/10.1016/j.compag.2023.107708
Zabihzadeh DMasoudifar M(2023)ZS-DML: Zero-Shot Deep Metric Learning approach for plant leaf disease classificationMultimedia Tools and Applications10.1007/s11042-023-17136-583:18(54147-54164)Online publication date: 30-Nov-2023
https://doi.org/10.1007/s11042-023-17136-5
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Full Text

View this article in Full Text.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View full text|Download PDF

View Issue’s Table of Contents