用于昆虫稳健分类的分布外检测算法

IF 7.6 1区 农林科学 Q1 AGRONOMY Plant Phenomics Pub Date : 2024-04-30 eCollection Date: 2024-01-01 DOI:10.34133/plantphenomics.0170
Mojdeh Saadati, Aditya Balu, Shivani Chiranjeevi, Talukder Zaki Jubery, Asheesh K Singh, Soumik Sarkar, Arti Singh, Baskar Ganapathysubramanian
{"title":"用于昆虫稳健分类的分布外检测算法","authors":"Mojdeh Saadati, Aditya Balu, Shivani Chiranjeevi, Talukder Zaki Jubery, Asheesh K Singh, Soumik Sarkar, Arti Singh, Baskar Ganapathysubramanian","doi":"10.34133/plantphenomics.0170","DOIUrl":null,"url":null,"abstract":"<p><p>Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.</p>","PeriodicalId":20318,"journal":{"name":"Plant Phenomics","volume":null,"pages":null},"PeriodicalIF":7.6000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11065417/pdf/","citationCount":"0","resultStr":"{\"title\":\"Out-of-Distribution Detection Algorithms for Robust Insect Classification.\",\"authors\":\"Mojdeh Saadati, Aditya Balu, Shivani Chiranjeevi, Talukder Zaki Jubery, Asheesh K Singh, Soumik Sarkar, Arti Singh, Baskar Ganapathysubramanian\",\"doi\":\"10.34133/plantphenomics.0170\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.</p>\",\"PeriodicalId\":20318,\"journal\":{\"name\":\"Plant Phenomics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11065417/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Plant Phenomics\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.34133/plantphenomics.0170\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Plant Phenomics","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.34133/plantphenomics.0170","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0

摘要

植物在生长周期中会遇到各种益虫和害虫。准确识别(即检测昆虫的存在)和分类(即确定昆虫的类型或类别)这些昆虫物种对于实施及时和适当的缓解战略至关重要。这种及时的行动具有重大的经济和环境影响。基于深度学习的方法已经产生了具有良好昆虫分类准确性的模型。研究人员的目标是在农业领域实施识别和分类模型,但当输入图像明显偏离训练分布时(如车辆、人类等图像,或尚未训练的模糊图像或昆虫类别),他们就会面临挑战。分布外(OOD)检测算法为克服这些挑战提供了一个令人兴奋的途径,因为它能确保模型不会对属于非昆虫和/或未经训练的昆虫类别的图像做出错误的分类预测。据我们所知,此前还没有人对 OOD 检测算法在解决农业问题方面的作用进行过深入探讨。在此,我们生成并评估了昆虫检测分类器上最先进的 OOD 算法的性能。这些算法代表了解决 OOD 问题的多种方法。具体来说,我们关注的是外显算法,即围绕训练有素的分类器而无需额外协同训练的算法。我们比较了三种 OOD 检测算法:(a) 最大软最大概率,该算法使用软最大值作为置信度得分;(b) 基于马哈拉诺比距离 (MAH) 的算法,该算法使用生成分类方法;以及 (c) 基于能量的算法,该算法将输入数据映射为一个标量值,称为能量。我们在三个性能轴上对这些 OOD 算法进行了一系列广泛的评估:(a) 基本模型的准确性:分类器的准确性如何影响 OOD 性能?(b) 与领域的不相似程度如何影响 OOD 性能?(c) 数据不平衡:OOD 性能对每类样本大小的不平衡有多敏感?在这些性能轴上评估 OOD 算法为确保训练有素的模型在野生环境中的稳健性能提供了实用指南,而这正是农业应用的关键考虑因素。基于上述分析,我们提出了最有效的 OOD 算法,作为昆虫分类器的包装器,具有最高的准确率。我们在论文中介绍了其 OOD 检测性能的结果。我们的结果表明,OOD 检测算法可以在不确定条件下放弃分类,从而大大提高用户对害虫分类的信任度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Out-of-Distribution Detection Algorithms for Robust Insect Classification.

Plants encounter a variety of beneficial and harmful insects during their growth cycle. Accurate identification (i.e., detecting insects' presence) and classification (i.e., determining the type or class) of these insect species is critical for implementing prompt and suitable mitigation strategies. Such timely actions carry substantial economic and environmental implications. Deep learning-based approaches have produced models with good insect classification accuracy. Researchers aim to implement identification and classification models in agriculture, facing challenges when input images markedly deviate from the training distribution (e.g., images like vehicles, humans, or a blurred image or insect class that is not yet trained on). Out-of-distribution (OOD) detection algorithms provide an exciting avenue to overcome these challenges as they ensure that a model abstains from making incorrect classification predictions on images that belong to non-insect and/or untrained insect classes. As far as we know, no prior in-depth exploration has been conducted on the role of the OOD detection algorithms in addressing agricultural issues. Here, we generate and evaluate the performance of state-of-the-art OOD algorithms on insect detection classifiers. These algorithms represent a diversity of methods for addressing an OOD problem. Specifically, we focus on extrusive algorithms, i.e., algorithms that wrap around a well-trained classifier without the need for additional co-training. We compared three OOD detection algorithms: (a) maximum softmax probability, which uses the softmax value as a confidence score; (b) Mahalanobis distance (MAH)-based algorithm, which uses a generative classification approach; and (c) energy-based algorithm, which maps the input data to a scalar value, called energy. We performed an extensive series of evaluations of these OOD algorithms across three performance axes: (a) Base model accuracy: How does the accuracy of the classifier impact OOD performance? (b) How does the level of dissimilarity to the domain impact OOD performance? (c) Data imbalance: How sensitive is OOD performance to the imbalance in per-class sample size? Evaluating OOD algorithms across these performance axes provides practical guidelines to ensure the robust performance of well-trained models in the wild, which is a key consideration for agricultural applications. Based on this analysis, we proposed the most effective OOD algorithm as wrapper for the insect classifier with highest accuracy. We presented the results of its OOD detection performance in the paper. Our results indicate that OOD detection algorithms can significantly enhance user trust in insect pest classification by abstaining classification under uncertain conditions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Plant Phenomics
Plant Phenomics Multiple-
CiteScore
8.60
自引率
9.20%
发文量
26
审稿时长
14 weeks
期刊介绍: Plant Phenomics is an Open Access journal published in affiliation with the State Key Laboratory of Crop Genetics & Germplasm Enhancement, Nanjing Agricultural University (NAU) and published by the American Association for the Advancement of Science (AAAS). Like all partners participating in the Science Partner Journal program, Plant Phenomics is editorially independent from the Science family of journals. The mission of Plant Phenomics is to publish novel research that will advance all aspects of plant phenotyping from the cell to the plant population levels using innovative combinations of sensor systems and data analytics. Plant Phenomics aims also to connect phenomics to other science domains, such as genomics, genetics, physiology, molecular biology, bioinformatics, statistics, mathematics, and computer sciences. Plant Phenomics should thus contribute to advance plant sciences and agriculture/forestry/horticulture by addressing key scientific challenges in the area of plant phenomics. The scope of the journal covers the latest technologies in plant phenotyping for data acquisition, data management, data interpretation, modeling, and their practical applications for crop cultivation, plant breeding, forestry, horticulture, ecology, and other plant-related domains.
期刊最新文献
Phenotyping of Panicle Number and Shape in Rice Breeding Materials Based on Unmanned Aerial Vehicle Imagery. Evaluating the Influence of Row Orientation and Crown Morphology on Growth of Pinus taeda L. with Drone-Based Airborne Laser Scanning. Cucumber Seedling Segmentation Network Based on a Multiview Geometric Graph Encoder from 3D Point Clouds. GSP-AI: An AI-Powered Platform for Identifying Key Growth Stages and the Vegetative-to-Reproductive Transition in Wheat Using Trilateral Drone Imagery and Meteorological Data. MLG-YOLO: A Model for Real-Time Accurate Detection and Localization of Winter Jujube in Complex Structured Orchard Environments.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1