pith. sign in

arxiv: 2606.02045 · v2 · pith:QIZ4VMGUnew · submitted 2026-06-01 · 💻 cs.CV · cs.AI

Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift

Adri\'an C\'anovas-Rodriguez , Miguel A. Gonz\'alez-Ill\'an , Maria Fernanda Garc\'ia-Cruz , Pedro Nortes Tortosa , Jos\'e Salvador Rubio-Asensio , Miguel A. Zamora Izquierdo , Juan Antonio Mart\'inez Navarro , Antonio F. Skarmeta This is my paper

Pith reviewed 2026-06-28 15:34 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords peach leaf damage classificationattention mechanismstransfer learningdomain shiftEfficientNetCBAMcrop disease detectiondeep learning in agriculture
0
0 comments X

The pith

Adding attention modules to EfficientNet models and applying transfer learning achieves over 93 percent accuracy in classifying peach leaf damage across different orchard conditions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that attention mechanisms improve the performance of EfficientNet models for identifying six types of damage on peach leaves in a 1,366-image benchmark dataset. The best result came from EfficientNetB5 with the Convolutional Block Attention Module at 93.3 percent accuracy. When tested on a separate 180-image local dataset collected under different conditions, transfer learning with EfficientNetB3 and attention reached 93 percent macro F1-score. This addresses the challenge of similar-looking symptoms and varying environments that hinder reliable diagnosis. The findings indicate that these enhancements support better generalization when models move from public images to real field settings.

Core claim

The authors demonstrate that integrating the Convolutional Block Attention Module into EfficientNet architectures, combined with transfer learning on a local dataset, yields the highest classification accuracy and robustness under domain shift for peach leaf damage detection, outperforming other tested models on both benchmark and local data.

What carries the argument

The Convolutional Block Attention Module (CBAM) that refines feature representations by focusing on important channels and spatial positions within EfficientNet backbones.

If this is right

  • CBAM integration particularly improves handling of minority damage classes.
  • Three fine-tuning strategies show that targeted transfer learning overcomes domain shift in local orchard images.
  • EfficientNetB3 with CBAM achieves the top 93 percent macro F1-score on the local four-class set.
  • Attention-enhanced models exhibit improved robustness to varying field conditions compared to baselines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar attention and transfer techniques could extend to classifying damage in other fruit crops facing comparable symptom overlaps.
  • Mobile deployment of these models might allow real-time orchard monitoring without extensive retraining per location.
  • Expanding the local dataset size or diversity would test whether the reported performance generalizes further.

Load-bearing premise

The 1,366-image benchmark and 180-image local collection capture the full visual variability and class distributions of damage in actual peach orchards under different conditions.

What would settle it

Evaluating the best model on additional peach leaf images from unseen orchards or seasons and finding accuracy substantially below 90 percent would indicate the generalization claims do not hold.

Figures

Figures reproduced from arXiv: 2606.02045 by Adri\'an C\'anovas-Rodriguez, Antonio F. Skarmeta, Jos\'e Salvador Rubio-Asensio, Juan Antonio Mart\'inez Navarro, Maria Fernanda Garc\'ia-Cruz, Miguel A. Gonz\'alez-Ill\'an, Miguel A. Zamora Izquierdo, Pedro Nortes Tortosa.

Figure 1
Figure 1. Figure 1: Representative examples of each class in the dataset. [PITH_FULL_IMAGE:figures/full_fig_p010_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Georeferenced position of the study plot designated for data acquisition and [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Representative examples of local leave images. In this case a healthy leave and [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: CBAM implementation scheme. Parameters H, W and C depends on each [PITH_FULL_IMAGE:figures/full_fig_p018_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Confusion matrices of representative models: EfficientNetB0 (light), [PITH_FULL_IMAGE:figures/full_fig_p025_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Class-wise comparison of F1, Recall, and Precision for EfficientNetB3, In [PITH_FULL_IMAGE:figures/full_fig_p027_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: F1 (macro) comparison before and after fine-tuning (FT) for each model. The [PITH_FULL_IMAGE:figures/full_fig_p034_7.png] view at source ↗
read the original abstract

Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and diseases, which often produce visually similar foliar symptoms. This overlap makes manual diagnosis difficult, especially across multiple fields with varying environmental conditions, highlighting the need for automated models with strong generalization ability. We propose an image-based classification approach for peach leaf damage detection. A benchmark dataset was created through manual annotation of publicly available images, consisting of 1,366 peach leaves across six damage categories. Several deep learning architectures were evaluated. EfficientNet models achieved the best results, with EfficientNetB0 reaching 92.9 percent accuracy, EfficientNetB3 achieving 91.5 percent, and EfficientNetB5 showing the strongest performance on minority classes. DenseNet121 reached 92.6 percent accuracy. The integration of the Convolutional Block Attention Module (CBAM) improved performance in several backbones, particularly EfficientNetB5 and InceptionV3, while showing limited or negative impact in others. The CBAM-enhanced EfficientNetB5 achieved the best overall accuracy of 93.3 percent. To evaluate robustness under realistic conditions, a local dataset of 180 images across four classes was collected, and transfer learning strategies were applied to address domain shift. Three fine-tuning strategies were tested. EfficientNetB3 combined with CBAM achieved the best performance in the local domain, reaching a 93 percent macro F1-score after transfer. Overall, attention-based models showed improved robustness for minority classes and better generalization across different field conditions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper creates a manually annotated benchmark of 1,366 peach leaf images in six damage classes and evaluates multiple CNN backbones with and without the Convolutional Block Attention Module (CBAM). EfficientNetB5+CBAM reaches 93.3% accuracy on the benchmark; on a separate local collection of 180 images in four classes, transfer learning with EfficientNetB3+CBAM yields 93% macro F1, which the authors interpret as evidence of improved robustness to domain shift.

Significance. If the local-domain numbers prove reliable, the work supplies concrete empirical support that attention modules can aid minority-class performance and cross-domain transfer in agricultural image classification, a practically relevant setting. The dual evaluation on a public-scale benchmark plus a field-collected set is a positive feature.

major comments (1)
  1. [Local dataset and transfer-learning experiments] The central claim of improved generalization under domain shift rests entirely on transfer results from the local 180-image, four-class collection. No train/validation/test split sizes, no standard deviations across repeated splits, no statistical comparison to non-CBAM baselines, and no quantification of how representative the 180 images are of orchard variability (lighting, cultivar, severity) are reported. This makes the 93% macro F1 indistinguishable from an optimistic draw and directly weakens the robustness conclusion.
minor comments (1)
  1. [Abstract] The abstract states that three fine-tuning strategies were tested but does not enumerate them or indicate which produced the reported best result.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our work. We address the major comment point-by-point below and commit to revisions that strengthen the reporting of the local-domain experiments.

read point-by-point responses

  1. Referee: The central claim of improved generalization under domain shift rests entirely on transfer results from the local 180-image, four-class collection. No train/validation/test split sizes, no standard deviations across repeated splits, no statistical comparison to non-CBAM baselines, and no quantification of how representative the 180 images are of orchard variability (lighting, cultivar, severity) are reported. This makes the 93% macro F1 indistinguishable from an optimistic draw and directly weakens the robustness conclusion.

    Authors: We agree that the current manuscript lacks sufficient experimental detail on the local dataset, which is necessary to fully support the domain-shift claims. In the revised version we will add: (i) the precise train/validation/test split ratios and sizes used for the 180 images, (ii) standard deviations obtained from repeated random splits or multiple runs, (iii) statistical significance tests (e.g., McNemar or paired t-tests) comparing CBAM-enhanced models against the corresponding non-CBAM baselines, and (iv) an expanded description of the local collection protocol that addresses variability in lighting, cultivars, and damage severity. These additions will allow readers to evaluate whether the reported 93 % macro F1 is robust or potentially optimistic. revision: yes

Circularity Check

0 steps flagged

No circularity; purely empirical results on held-out image sets

full rationale

The paper evaluates standard deep learning architectures (EfficientNet variants, DenseNet, InceptionV3) with optional CBAM attention on two image datasets: a 1,366-image benchmark and a 180-image local collection. All reported figures (92.9% accuracy, 93.3% accuracy, 93% macro F1) are direct measurements of model performance on held-out test images after training or fine-tuning. No equations, derivations, or parameter-fitting steps appear; no quantity is defined in terms of itself, no fitted hyper-parameter is relabeled as a prediction, and no uniqueness theorems or self-citations are invoked to justify model choices. The work is self-contained empirical ML evaluation with no load-bearing self-referential structure.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The performance claims rest on the unstated premise that the six damage categories are visually separable by convolutional features and that the two datasets share enough visual statistics for transfer learning to succeed; no free parameters or invented entities are introduced beyond standard model weights.

axioms (1)
  • domain assumption Convolutional neural networks trained on labeled leaf images can learn features that distinguish damage categories even when imaging conditions change between datasets.
    Invoked to justify both the benchmark evaluation and the transfer-learning results on the local domain.

pith-pipeline@v0.9.1-grok · 5884 in / 1404 out tokens · 27193 ms · 2026-06-28T15:34:27.635247+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

134 extracted references · 48 canonical work pages

  1. [3]

    Cross-comparative review of Machine learning for plant disease detection: apple, cassava, cotton and potato plants , journal =

    James Daniel Omaye and Emeka Ogbuju and Grace Ataguba and Oluwayemisi Jaiyeoba and Joseph Aneke and Francisca Oladipo , keywords =. Cross-comparative review of Machine learning for plant disease detection: apple, cassava, cotton and potato plants , journal =. 2024 , issn =. doi:https://doi.org/10.1016/j.aiia.2024.04.002 , url =

    work page doi:10.1016/j.aiia.2024.04.002 2024

  2. [7]

    YOLO-light-pruned: A lightweight model for monitoring maize seedling count and leaf age using near-ground and UAV RGB images , journal =

    Tiantian Jiang and Liang Li and Zhen Zhang and Xun Yu and Yanqin Zhu and Liming Li and Yadong Liu and Yali Bai and Ziqian Tang and Shuaibing Liu and Yan Zhang and Zheng Duan and Dameng Yin and Xiuliang Jin , keywords =. YOLO-light-pruned: A lightweight model for monitoring maize seedling count and leaf age using near-ground and UAV RGB images , journal =....

    work page doi:10.1016/j.aiia.2025.10.002 2026

  3. [8]

    Using UAV-based multispectral images and CGS-YOLO algorithm to distinguish maize seeding from weed , journal =

    Boyi Tang and Jingping Zhou and Chunjiang Zhao and Yuchun Pan and Yao Lu and Chang Liu and Kai Ma and Xuguang Sun and Ruifang Zhang and Xiaohe Gu , keywords =. Using UAV-based multispectral images and CGS-YOLO algorithm to distinguish maize seeding from weed , journal =. 2025 , issn =. doi:https://doi.org/10.1016/j.aiia.2025.02.007 , url =

    work page doi:10.1016/j.aiia.2025.02.007 2025

  4. [9]

    A comprehensive survey on weed and crop classification using machine learning and deep learning , journal =

    Faisal Dharma Adhinata and Wahyono and Raden Sumiharto , keywords =. A comprehensive survey on weed and crop classification using machine learning and deep learning , journal =. 2024 , issn =. doi:https://doi.org/10.1016/j.aiia.2024.06.005 , url =

    work page doi:10.1016/j.aiia.2024.06.005 2024

  5. [11]

    2015 , howpublished=

    Keras , author=. 2015 , howpublished=

    2015

  6. [12]

    EfficientNet-Based Robust Recognition of Peach Plant Diseases in Field Images , volume =

    Farman, Haleem and Ahmad, Jamil and Jan, Bilal and Shahzad, Yasir and Abdullah, Muhammad and Ullah, Atta , year =. EfficientNet-Based Robust Recognition of Peach Plant Diseases in Field Images , volume =. Computers, Materials & Continua , doi =

  7. [14]

    Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation

    Li, Dingcheng and Chen, Zheng and Cho, Eunah and Hao, Jie and Liu, Xiaohu and Xing, Fan and Guo, Chenlei and Liu, Yang. Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2...

    work page doi:10.18653/v1/2022.naacl-main.398 2022

  8. [16]

    2017 , eprint=

    MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , author=. 2017 , eprint=

    2017

  9. [17]

    Deep Learning for Plant Diseases: Detection and Saliency Map Visualisation

    Brahimi, Mohammed and Arsenovic, Marko and Laraba, Sohaib and Sladojevic, Srdjan and Boukhalfa, Kamel and Moussaoui, Abdelouhab. Deep Learning for Plant Diseases: Detection and Saliency Map Visualisation. Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent. 2018

    2018

  10. [18]

    2019 , eprint=

    MobileNetV2: Inverted Residuals and Linear Bottlenecks , author=. 2019 , eprint=

    2019

  11. [19]

    2019 , eprint=

    Searching for MobileNetV3 , author=. 2019 , eprint=

    2019

  12. [20]

    2020 , eprint=

    EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , author=. 2020 , eprint=

    2020

  13. [21]

    2015 , eprint=

    Deep Residual Learning for Image Recognition , author=. 2015 , eprint=

    2015

  14. [22]

    2015 , eprint=

    Very Deep Convolutional Networks for Large-Scale Image Recognition , author=. 2015 , eprint=

    2015

  15. [23]

    2015 , eprint=

    Rethinking the Inception Architecture for Computer Vision , author=. 2015 , eprint=

    2015

  16. [24]

    2019 , eprint=

    Squeeze-and-Excitation Networks , author=. 2019 , eprint=

    2019

  17. [25]

    2018 , eprint=

    CBAM: Convolutional Block Attention Module , author=. 2018 , eprint=

    2018

  18. [26]

    2017 , eprint=

    Adam: A Method for Stochastic Optimization , author=. 2017 , eprint=

    2017

  19. [27]

    ImageNet: A large-scale hierarchical image database , year=

    Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Kai Li and Li Fei-Fei , booktitle=. ImageNet: A large-scale hierarchical image database , year=

  20. [29]

    Jocher, Glenn and Qiu, Jing and Chaurasia, Ayush , title =

  21. [30]

    Plant Disease Detection Using Machine Learning , year=

    Ramesh, Shima and Hebbar, Ramachandra and M., Niveditha and R., Pooja and N., Prasad Bhat and N., Shashank and P.V., Vinod , booktitle=. Plant Disease Detection Using Machine Learning , year=

  22. [31]

    A survey of detecting leaf diseases using machine learning and deep learning in various crops , volume =

    T, Thilagraj and Kareem, Abdul and Kumara, Varun and Naik, Utkrishna and Poojary, Sanjana and R, Bharath , year =. A survey of detecting leaf diseases using machine learning and deep learning in various crops , volume =. IAES International Journal of Artificial Intelligence (IJ-AI) , doi =

  23. [32]

    Tomato leaves diseases detection approach based on Support Vector Machines , booktitle =

    Ali, Mona and Mokhtar, Usama and Hassanien, Aboul Ella and Hefny, Hesham , year =. Tomato leaves diseases detection approach based on Support Vector Machines , booktitle =

  24. [33]

    Asif and Talukder, Kamrul Hasan , booktitle=

    Iqbal, Md. Asif and Talukder, Kamrul Hasan , booktitle=. Detection of Potato Disease Using Image Segmentation and Machine Learning , year=

  25. [34]

    K. J. Mohan and M. Balasubramanian and S. Palanivel , title =. International Journal of Computer Applications , volume =. 2016 , doi =

    2016

  26. [35]

    Plant Leaf Disease Prediction , volume =

    Monigari, Vaishnavi , year =. Plant Leaf Disease Prediction , volume =. International Journal for Research in Applied Science and Engineering Technology , doi =

  27. [37]

    Rama , booktitle=

    M, Teenu Sahasra and S, Sai Kumari and S, Sai Meghana and Devi, P. Rama , booktitle=. Leaf Disease Detection Using Deep Learning , year=

  28. [39]

    International Conference on Electronic Governance with Emerging Technologies , pages=

    Leaf Diseases Detection in Peach Using EfficientNet , author=. International Conference on Electronic Governance with Emerging Technologies , pages=. 2024 , organization=

    2024

  29. [40]

    Stefani , journal =

    E. Stefani , journal =. ECONOMIC SIGNIFICANCE AND CONTROL OF BACTERIAL SPOT/CANKER OF STONE FRUITS CAUSED BY XANTHOMONAS ARBORICOLA pv. PRUNI , urldate =

  30. [41]

    Bacteria , VOLUME =

    Sakata, Nanami and Ishiga, Yasuhiro , TITLE =. Bacteria , VOLUME =. 2025 , NUMBER =

    2025

  31. [44]

    International Journal of Molecular Sciences , VOLUME =

    Kopecká, Romana and Kameniarová, Michaela and Černý, Martin and Brzobohatý, Břetislav and Novák, Jan , TITLE =. International Journal of Molecular Sciences , VOLUME =. 2023 , NUMBER =

    2023

  32. [46]

    Plant growth regulation , volume=

    The effects of mechanically-induced stress in plants—a review , author=. Plant growth regulation , volume=. 1986 , publisher=

    1986

  33. [47]

    Experimental and Applied Acarology , volume=

    Do plant mites commonly prefer the underside of leaves? , author=. Experimental and Applied Acarology , volume=. 2011 , publisher=

    2011

  34. [48]

    , TITLE =

    Situngu, Sivuyisiwe and Barker, Nigel P. , TITLE =. Forests , VOLUME =. 2024 , NUMBER =

    2024

  35. [49]

    Insects , VOLUME =

    Möth, Stefan and Walzer, Andreas and Redl, Markus and Petrović, Božana and Hoffmann, Christoph and Winter, Silvia , TITLE =. Insects , VOLUME =. 2021 , NUMBER =

    2021

  36. [53]

    Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration , year=

    Ul Amin, Sareer and Sibtain Abbas, Muhammad and Kim, Bumsoo and Jung, Yonghoon and Seo, Sanghyun , journal=. Enhanced Anomaly Detection in Pandemic Surveillance Videos: An Attention Approach With EfficientNet-B0 and CBAM Integration , year=

  37. [54]

    ICTAR , month =

    Gök, Ali and Yurdakul, Mustafa and Tasdemir, Sakir , year =. ICTAR , month =

  38. [55]

    2018 , eprint=

    Densely Connected Convolutional Networks , author=. 2018 , eprint=

    2018

  39. [56]

    2016 , eprint=

    You Only Look Once: Unified, Real-Time Object Detection , author=. 2016 , eprint=

    2016

  40. [57]

    2025 , eprint=

    YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions , author=. 2025 , eprint=

    2025

  41. [58]

    2024 , eprint=

    YOLOv11: An Overview of the Key Architectural Enhancements , author=. 2024 , eprint=

    2024

  42. [60]

    2019 , eprint=

    PyTorch: An Imperative Style, High-Performance Deep Learning Library , author=. 2019 , eprint=

    2019

  43. [61]

    2019 , eprint=

    An introduction to domain adaptation and transfer learning , author=. 2019 , eprint=

    2019

  44. [62]

    2020 , eprint=

    A Comprehensive Survey on Transfer Learning , author=. 2020 , eprint=

    2020

  45. [63]

    Learning and Domain Adaptation , booktitle=

    Mansour, Yishay , year =. Learning and Domain Adaptation , booktitle=

  46. [65]

    Horticulturae , volume=

    Influence of climate change on metabolism and biological characteristics in perennial woody fruit crops in the Mediterranean environment , author=. Horticulturae , volume=. 2022 , publisher=

    2022

  47. [66]

    Regional environmental change , volume=

    Climate change impacts on winter chill in Mediterranean temperate fruit orchards , author=. Regional environmental change , volume=. 2023 , publisher=

    2023

  48. [67]

    Horticulturae , volume=

    Effects of Elevated Temperature on the Phenology and Fruit Shape of the Early-Maturing Peach Cultivar ‘Mihong’ , author=. Horticulturae , volume=. 2025 , publisher=

    2025

  49. [68]

    Agricultural and Forest Meteorology , volume=

    Shifts in the thermal niche of fruit trees under climate change: The case of peach cultivation in France , author=. Agricultural and Forest Meteorology , volume=. 2021 , publisher=

    2021

  50. [69]

    International Journal of Environment and Climate Change , volume=

    Effects of Climate Change on Fruit Growing: Risks and Solutions for the Future , author=. International Journal of Environment and Climate Change , volume=. 2025 , doi=

    2025

  51. [70]

    Insects , volume=

    Impact of Climate Change on Peach Fruit Moth Phenology: A Regional Perspective from China , author=. Insects , volume=. 2024 , publisher=

    2024

  52. [71]

    leaves in two agroecosystems , author=

    Diversity of the organisms in the Prunus persicae L. leaves in two agroecosystems , author=. I+ D Revista de Investigaciones , volume=. 2024 , url=

    2024

  53. [72]

    The impact of global warming on fruit crops and mitigation strategies: A comprehensive review , author=. Agronom. 2025 , publisher=

    2025

  54. [73]

    Agricultural Systems , volume=

    Phenological and epidemiological impacts of climate change on peach production , author=. Agricultural Systems , volume=. 2024 , publisher=

    2024

  55. [74]

    International Journal of Molecular Sciences , volume=

    Enhancing abiotic stress resilience in Mediterranean woody perennial fruit crops: Genetic, epigenetic, and microbial molecular perspectives in the face of climate change , author=. International Journal of Molecular Sciences , volume=. 2025 , publisher=

    2025

  56. [75]

    The Horticulture Journal , pages=

    Meteorological Responses of Fruit Trees, Impact of Climate Change on Fruit Production, and Adaptation Strategies , author=. The Horticulture Journal , pages=. 2025 , publisher=

    2025

  57. [76]

    Scientific Reports , volume=

    Plant leaf disease detection using vision transformers for precision agriculture , author=. Scientific Reports , volume=. 2025 , url=

    2025

  58. [77]

    Proceedings of the Entomological Society of Washington , volume=

    Population Dynamics of Peach Silver Mite Aculus fockeui (Nalepa and Trouessart)(Acari: Eriophyidae) on Plum, Prunus domestica, and Peach, Prunus persica,(Rosaceae) in Yalova-Turkey , author=. Proceedings of the Entomological Society of Washington , volume=. 2023 , publisher=

    2023

  59. [78]

    Abiotic Stress Management in Fruit Crops , isbn =

    Manju and Agrawal, Sarita and Alam, Md and Mir, Muzafar and Singh, Kh and Sharma, Aman , year =. Abiotic Stress Management in Fruit Crops , isbn =

  60. [79]

    Artificial Intelligence Review , volume=

    Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture , author=. Artificial Intelligence Review , volume=. 2025 , publisher=

    2025

  61. [80]

    Frontiers in Plant Science , volume=

    A review of plant leaf disease identification by deep learning algorithms , author=. Frontiers in Plant Science , volume=. 2025 , publisher=

    2025

  62. [81]

    J , volume=

    Plant Leaf Disease Detection Using Deep Learning: A Multi-Dataset Approach , author=. J , volume=. 2025 , publisher=

    2025

  63. [82]

    , author=

    PeachNet: Peach Diseases Detection for Automatic Harvesting. , author=. Computers, Materials & Continua , volume=. 2021 , url=

    2021

  64. [84]

    BMC Plant Biology , volume=

    Deep learning technique for plant disease classification and pest detection and model explainability elevating agricultural sustainability , author=. BMC Plant Biology , volume=. 2025 , publisher=

    2025

  65. [85]

    Plants , volume=

    Plant and disease recognition based on PMF pipeline domain adaptation method: Using bark images as meta-dataset , author=. Plants , volume=. 2023 , publisher=

    2023

  66. [86]

    Computers and Electronics in Agriculture , volume=

    Advancing plant disease classification: A robust and generalized approach with transformer-fused convolution and Wasserstein domain adaptation , author=. Computers and Electronics in Agriculture , volume=. 2024 , publisher=

    2024

  67. [87]

    pruni in China , author=

    Identification, genetic diversity, and chemical control of Xanthomonas arboricola pv. pruni in China , author=. Plant Disease , volume=. 2022 , publisher=

    2022

  68. [88]

    pruni, causal agent of bacterial spot of stone fruits and almond: its genomic and phenotypic characteristics in the X

    Xanthomonas arboricola pv. pruni, causal agent of bacterial spot of stone fruits and almond: its genomic and phenotypic characteristics in the X. arboricola species context , author=. Molecular plant pathology , volume=. 2018 , publisher=

    2018

  69. [89]

    Insects , volume=

    Management of Panonychus ulmi with various miticides and insecticides and their toxicity to predatory mites conserved for biological mite control in eastern US Apple Orchards , author=. Insects , volume=. 2023 , publisher=

    2023

  70. [91]

    PLoS One , volume=

    Comparison of absorption and excretion of test compounds in sucking versus chewing pests , author=. PLoS One , volume=. 2025 , publisher=

    2025

  71. [92]

    , author Agarwal, A

    author Abadi, M. , author Agarwal, A. , author Barham, P. , author Brevdo, E. , author Chen, Z. , author Citro, C. , author Corrado, G.S. , author Davis, A. , author Dean, J. , author Devin, M. , author Ghemawat, S. , author Goodfellow, I. , author Harp, A. , author Irving, G. , author Isard, M. , author Jia, Y. , author Jozefowicz, R. , author Kaiser, L....

    2015

  72. [93]

    , author Farman, H

    author Ahmad, J. , author Farman, H. , year 2024 . title Dataset: Efficientnet-based robust recognition of peach plant diseases in field images . howpublished Mendeley Data, V1 . https://data.mendeley.com/datasets/3pmj85snvw/1, :10.17632/3pmj85snvw.1

    work page doi:10.17632/3pmj85snvw.1 2024

  73. [94]

    , author Alyami, H

    author Alosaimi, W. , author Alyami, H. , author Uddin, M.I. , year 2021 . title Peachnet: Peach diseases detection for automatic harvesting. journal Computers, Materials & Continua volume 67 . https://doi.org/10.32604/cmc.2021.014950

    work page doi:10.32604/cmc.2021.014950 2021

  74. [95]

    , author Gole, P

    author Bedi, P. , author Gole, P. , year 2021 . title Plant disease detection using hybrid model based on convolutional autoencoder and convolutional neural network . journal Artificial Intelligence in Agriculture volume 5 , pages 90--101 . https://www.sciencedirect.com/science/article/pii/S2589721721000180, :https://doi.org/10.1016/j.aiia.2021.05.002

    work page doi:10.1016/j.aiia.2021.05.002 2021

  75. [96]

    , year 1986

    author Biddington, N.L. , year 1986 . title The effects of mechanically-induced stress in plants—a review . journal Plant growth regulation volume 4 , pages 103--123

    1986

  76. [97]

    , author Neer, W.C

    author Body, M.J.A. , author Neer, W.C. , author Vore, C. , author Lin, C.H. , author Vu, D.C. , author Schultz, J.C. , author Cocroft, R.B. , author Appel, H.M. , year 2019 . title Caterpillar chewing vibrations cause changes in plant hormones and volatile emissions in arabidopsis thaliana . journal Frontiers in Plant Science volume Volume 10 - 2019 . ht...

    work page doi:10.3389/fpls.2019.00810 2019

  77. [98]

    , author Arsenovic, M

    author Brahimi, M. , author Arsenovic, M. , author Laraba, S. , author Sladojevic, S. , author Boukhalfa, K. , author Moussaoui, A. , year 2018 . title Deep Learning for Plant Diseases: Detection and Saliency Map Visualisation . publisher Springer International Publishing , address Cham . chapter chapter 8 . pp. pages 93--117 . https://doi.org/10.1007/978...

    work page doi:10.1007/978-3-319-90403-0_6 2018

  78. [99]

    , author Iglovikov, V.I

    author Buslaev, A. , author Iglovikov, V.I. , author Khvedchenya, E. , author Parinov, A. , author Druzhinin, M. , author Kalinin, A.A. , year 2020 . title Albumentations: Fast and flexible image augmentations . journal Information volume 11 , pages 125 . http://dx.doi.org/10.3390/info11020125, :10.3390/info11020125

    work page doi:10.3390/info11020125 2020

  79. [100]

    , et al., year 2015

    author Chollet, F. , et al., year 2015 . title Keras . howpublished https://keras.io

    2015

  80. [101]

    , author Li, K

    author Cui, Z. , author Li, K. , author Kang, C. , author Wu, Y. , author Li, T. , author Li, M. , year 2023 . title Plant and disease recognition based on pmf pipeline domain adaptation method: Using bark images as meta-dataset . journal Plants volume 12 , pages 3280 . https://doi.org/10.3390/plants12183280

    work page doi:10.3390/plants12183280 2023

Showing first 80 references.