The impact of fine-tuning paradigms on unknown plant diseases recognition.
Few-shot learning
Open-set recognition
Out-of-distribution detection
Plant disease recognition
Visual prompt
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
02 Aug 2024
02 Aug 2024
Historique:
received:
09
01
2024
accepted:
05
07
2024
medline:
3
8
2024
pubmed:
3
8
2024
entrez:
2
8
2024
Statut:
epublish
Résumé
Plant diseases pose significant threats to agriculture, impacting both food safety and public health. Traditional plant disease detection systems are typically limited to recognizing disease categories included in the training dataset, rendering them ineffective against new disease types. Although out-of-distribution (OOD) detection methods have been proposed to address this issue, the impact of fine-tuning paradigms on these methods has been overlooked. This paper focuses on studying the impact of fine-tuning paradigms on the performance of detecting unknown plant diseases. Currently, fine-tuning on visual tasks is mainly divided into visual-based models and visual-language-based models. We first discuss the limitations of large-scale visual language models in this task: textual prompts are difficult to design. To avoid the side effects of textual prompts, we futher explore the effectiveness of purely visual pre-trained models for OOD detection in plant disease tasks. Specifically, we employed five publicly accessible datasets to establish benchmarks for open-set recognition, OOD detection, and few-shot learning in plant disease recognition. Additionally, we comprehensively compared various OOD detection methods, fine-tuning paradigms, and factors affecting OOD detection performance, such as sample quantity. The results show that visual prompt tuning outperforms fully fine-tuning and linear probe tuning in out-of-distribution detection performance, especially in the few-shot scenarios. Notably, the max-logit-based on visual prompt tuning achieves an AUROC score of 94.8
Identifiants
pubmed: 39095389
doi: 10.1038/s41598-024-66958-2
pii: 10.1038/s41598-024-66958-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
17900Subventions
Organisme : National Research Foundation of Korea
ID : NRF-2021R1A2C1012174
Organisme : National Research Foundation of Korea
ID : 2019R1A6A1A09031717
Organisme : Rural Development Administration
ID : 1545027569
Informations de copyright
© 2024. The Author(s).
Références
Carroll, C. L., Carter, C. A., Goodhue, R. E. & Lawell, C.-Y. Crop disease and agricultural productivity: Evidence from a dynamic structural model of verticillium wilt management. In Agricultural Productivity and Producer Behavior, 217–249 (University of Chicago Press, 2018).
Savary, S. et al. The global burden of pathogens and pests on major food crops. Nat. Ecol. Evol. 3, 430–439 (2019).
doi: 10.1038/s41559-018-0793-y
pubmed: 30718852
Li, L., Zhang, S. & Wang, B. Plant disease detection and classification by deep learning-a review. IEEE Access 9, 56683–56698 (2021).
doi: 10.1109/ACCESS.2021.3069646
Shafik, W., Tufail, A., Namoun, A., De Silva, L. C. & Apong, R. A. A. H. M. A systematic literature review on plant disease detection: Techniques, dataset availability, challenges, future trends, and motivations. IEEE Access 11, 59174–59203 (2023).
doi: 10.1109/ACCESS.2023.3284760
Nazki, H., Yoon, S., Fuentes, A. & Park, D. S. Unsupervised image translation using adversarial networks for improved plant disease recognition. Comput. Electron. Agric. 168, 105117 (2020).
doi: 10.1016/j.compag.2019.105117
Tian, L. et al. VMF-SSD: A novel v-space based multi-scale feature fusion SSD for apple leaf disease detection. IEEE/ACM Trans. Comput. Biol. Bioinform. 20, 2016–2028 (2022).
doi: 10.1109/TCBB.2022.3229114
Dong, J. et al. Data-centric annotation analysis for plant disease detection: Strategy, consistency, and performance. Front. Plant Sci. 13, 1037655 (2022).
doi: 10.3389/fpls.2022.1037655
pubmed: 37082512
pmcid: 10112485
Dong, J., Fuentes, A., Yoon, S., Kim, H. & Park, D. S. An iterative noisy annotation correction model for robust plant disease detection. Front. Plant Sci. 14, 1238722 (2023).
doi: 10.3389/fpls.2023.1238722
pubmed: 37941667
pmcid: 10628849
Du, X., Wang, Z., Cai, M. & Li, Y. VOS: Learning What You Don't Know by Virtual Outlier Synthesis. International Conference on Learning Representations (ICLR, 2022).
Xiong, H. et al. From open set to closed set: Supervised spatial divide-and-conquer for object counting. Int. J. Comput. Vis. 131, 1722–1740 (2023).
doi: 10.1007/s11263-023-01782-1
Hendrycks, D. & Gimpel, K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016).
Fuentes, A., Yoon, S., Kim, T. & Park, D. S. Open set self and across domain adaptation for tomato disease recognition with deep learning techniques. Front. Plant Sci. 12, 758027 (2021).
doi: 10.3389/fpls.2021.758027
pubmed: 34956261
pmcid: 8702618
Ming, Y. et al. Delving into out-of-distribution detection with vision-language representations. Adv. Neural Inf. Process. Syst. 35, 35087–35102 (2022).
Ming, Y. & Li, Y. How does fine-tuning impact out-of-distribution detection for vision-language models?. Int. J. Comput. Vis. 132(2), 596–609 (2024).
doi: 10.1007/s11263-023-01895-7
Miyai, A., Yu, Q., Irie, G. & Aizawa, K. LoCoOp: Few-shot out-of-distribution detection via prompt learning. In Thirty-Seventh Conference on Neural Information Processing Systems (2023).
Fort, S., Ren, J. & Lakshminarayanan, B. Exploring the limits of out-of-distribution detection. Adv. Neural Inf. Process. Syst. 34, 7068–7081 (2021).
Huang, R. & Li, Y. MOS: Towards scaling out-of-distribution detection for large semantic space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8710–8719 (2021).
Lee, K., Lee, K., Lee, H. & Shin, J. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In Advances in Neural Information Processing Systems, Vol. 31 (2018).
Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, 8748–8763 (PMLR, 2021).
Zhou, K., Yang, J., Loy, C. C. & Liu, Z. Learning to prompt for vision-language models. Int. J. Comput. Vis. 130, 2337–2348 (2022).
doi: 10.1007/s11263-022-01653-1
Zhou, K., Yang, J., Loy, C. C. & Liu, Z. Conditional prompt learning for vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16816–16825 (2022).
Yang, J., Zhou, K., Li, Y. & Liu, Z. Generalized out-of-distribution detection: A survey. Int. J. Comput. Vis. 1–28 (2024).
Liang, S., Li, Y. & Srikant, R. Enhancing the reliability of out-of-distribution image detection in neural networks. In International Conference on Learning Representations (2018).
Hendrycks, D. et al. Scaling out-of-distribution detection for real-world settings. In International Conference on Machine Learning, 8759–8773 (PMLR, 2022).
Liu, W., Wang, X., Owens, J. & Li, Y. Energy-based out-of-distribution detection. Adv. Neural. Inf. Process. Syst. 33, 21464–21475 (2020).
Lin, Z., Roy, S. D. & Li, Y. Mood: Multi-level out-of-distribution detection. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, 15313–15323 (2021).
Hendrycks, D., Lee, K. & Mazeika, M. Using pre-training can improve model robustness and uncertainty. In international Conference on Machine Learning, 2712–2721 (PMLR, 2019).
Kirillov, A. et al. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4015–4026 (ICCV, 2023).
Kornblith, S., Shlens, J. & Le, Q. V. Do better imagenet models transfer better? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2661–2671 (2019).
Jia, M. et al. Visual prompt tuning. In European Conference on Computer Vision, 709–727 (Springer, 2022).
Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (2020).
Dhamodharan. Cotton plant disease (2023).
Ahmed, S. I. et al. MangoLeafBD: A comprehensive image dataset to classify diseased and healthy mango leaves. Data Brief 47, 108941 (2023).
doi: 10.1016/j.dib.2023.108941
pubmed: 36819904
pmcid: 9932726
Afzaal, U., Bhattarai, B., Pandeya, Y. R. & Lee, J. An instance segmentation model for strawberry diseases based on mask R-CNN. Sensors 21, 6565 (2021).
doi: 10.3390/s21196565
pubmed: 34640893
pmcid: 8513076
Hughes, D., Salathé, M. et al. An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060 (2015).
Chen, Z. et al. Vision transformer adapter for dense predictions. In The Eleventh International Conference on Learning Representations (ICLR, 2023).
Yao, Y. et al. W-transformer: Accurate cobb angles estimation by using a transformer-based hybrid structure. Med. Phys. 49, 3246–3262 (2022).
doi: 10.1002/mp.15561
pubmed: 35194794
Ryu, S., Koo, S., Yu, H. & Lee, G. G. Out-of-domain detection based on generative adversarial network. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 714–718 (2018).
Powers, D. M. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061 (2020).
Gunawardana, A. & Shani, G. A survey of accuracy evaluation metrics of recommendation tasks. J. Mach. Learn. Res. 10, 2935–2962 (2009).
Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255 (IEEE, 2009).
Parkhi, O. M., Vedaldi, A., Zisserman, A. & Jawahar, C. Cats and dogs. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, 3498–3505 (IEEE, 2012).
Zaken, E. B., Ravfogel, S. & Goldberg, Y. BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021).
Yosinski, J., Clune, J., Bengio, Y. & Lipson, H. How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems, Vol. 27 (2014).