AI Chat Paper
Discover the SciOpen Platform and Achieve Your Research Goals with Ease.
Search articles, authors, keywords, DOl and etc.
{{expandStatus?'Exit ':''}}Advanced Search
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.
Skendžić S, Zovko M, Živković IP, Lešić V, Lemić D. The impact of climate change on agricultural insect pests. Insects. 2021;12(5): 440.
Noar RD, Jahant-Miller CJ, Emerine S, Hallberg R. Early warning systems as a component of integrated pest management to prevent the introduction of exotic pests. J Integ Pest Manag. 2021;12(1):16.
Heeb L, Jenner E, Cock MJW. Climate-smart pest management: Building 463 resilience of farms and landscapes to changing pest threats. J Pest Sci. 2019;92(63):951–969.
Kim K-N, Huang QY, Lei CL. Advances in insect phototaxis and application to pest management: A review. Pest Manag Sci. 2019;75(12):3135–3143.
Naik S, Patel B. Machine vision based fruit classification and grading-a review. Int J Comput Appl. 2017;170(9):22–34.
Singh A, Ganapathysubramanian B, Singh AK, Sarkar S. Machine learning for high-throughput stress phenotyping in plants. Trends Plant Sci. 2016;21(2):110–124.
Singh AK, Ganapathysubramanian B, Sarkar S, Singh A. Deep learning for plant stress phenotyping: Trends and future perspectives. Trends Plant Sci. 2018;23(10):883–898.
Xia D, Chen P, Wang B, Zhang J, Xie C. Insect detection and classification based on an improved convolutional neural network. Sensors. 2018;180(12):4169.
Chen Y, Why A, Batista G, Mafra-Neto A, Keogh E. Flying insect detection and classification with inexpensive sensors. J Vis Exp. 2014;(92): Article e52111.
Høye TT, Ärje J, Bjerge K, Hansen OLP, Iosifidis A, Leese F, Mann HMR, Meissner K, Melvad C, Raitoharju J. Deep learning and computer vision will transform entomology. Proc Natl Acad Sci U S A. 2021;118(2): Article e2002545117.
Kar S, Nagasubramanian K, Elango D, Carroll ME, Abel CA, Nair A, Mueller DS, O'Neal ME, Singh AK, Sarkar S, et al. Self-supervised learning improves agricultural pest classification. AI Agric Food Syst. 2021.
Ebrahimi M, Khoshtaghaza MH, Minaei S, Jamshidi B. Vision-based pest detection based on SVM classification method. Comput Electron Agric. 2017;137:52–58.
Kasinathan T, Singaraju D, Uyyala SR. Insect classification and detection in field crops using modern machine learning techniques. Inform Process Agric. 2021;8(1):446–457.
Tetila EC, Brandoli B, Astolfi G, NAS B, Amorim WP, Roel AR, Pistori H. Detection and classification of soybean pests using deep learning with UAV images. Comput Electron Agric. 2020;179(2020): Article 105836.
Li Y, Wang H, Dang LM, Sadeghi-Niaraki A, Moon H. Crop pest recognition in natural scenes using convolutional neural networks. Comput Electron Agric. 2020;169: Article 105174.
Dong D, Nagasubramanian K, Wang R, Frei UK, Jubery TZ, Lübberstedt T, Ganapathysubramanian B. Self-supervised maize kernel classification and segmentation for embryo identification. Front Plant Sci. 2023;14:1108355.
Nagasubramanian K, Singh A, Singh A, Sarkar S, Ganapathysubramanian B. Plant phenotyping with limited annotation: Doing more with less. Plant Phenome J. 2022;5(1): Article e20051.
Duncan J, Kapoor R, Agarwal A, Singh C, Yu B. VeridicalFlow: A python package for building trustworthy data science pipelines with PCS. J Open Source Softw. 2022;7(69):3895.
Gadiraju U, Yang J. What can crowd computing do for the next generation of AI 509 systems? CSW@ NeurIPS. 2020;7–13.
Chatzimparmpas A, Martins RM, Jusufi I, Kucher K, Rossi F, Kerren A. The state of the art in enhancing trust in machine learning models with the use of visualizations. Comput Graph Forum. 2020;39(3):713–756.
Meyer GP. Learning an uncertainty-aware object detector for autonomous driving. IEEE/RSJ Int Conf Intell Robot Syst. 2020;2020:10521–10527.
Linmans J, van der Laak J, Litjens G. Efficient out-of-distribution detection in digital pathology using multi-head convolutional neural networks. MIDL. 2020;465–478.
Farid A, Veer S, Majumdar A. Task-driven out-of-distribution detection with statistical guarantees for robot learning. Conf Robot Learn. 2022;970–980.
Boyer P, Burns D, Whyne C. Out-of-distribution detection of human activity recognition with smartwatch inertial sensors. Sensors. 2021;21(5):1669.
Liu W. Energy-based out-of-distribution detection. Adv Neural Inf Process Syst. 2020;33:21464–21475.
Ren J, Liu PJ, Fertig E, Snoek J, Poplin R, Pristo MA, Dillon JV, Lakshminarayanan B. Likelihood ratios for out-of-distribution detection. Adv Neural Inf Process Syst. 2019;32.
Roy AG, Ren J, Azizi S, Loh A, Natarajan V, Mustafa B, Pawlowski N, Freyberg J, Liu Y, Beaver Z, et al. Does your dermatology classifier know what it doesn’t know? Detecting the long-tail of unseen conditions. Med Image Anal. 2022;75: Article 102274.
Fort S, Ren J, Lakshminarayanan B. Exploring the limits of out-of-distribution detection. Adv Neural Inf Process Syst. 2021;34:7068–7081.
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, et al. ImageNet large scale visual recognition challenge. Int J Comput Vision. 2015;115:211–252.
Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0).
京公网安备11010802044758号