Towards Improved Performance on Plant Disease Recognition with Symptoms Specific Annotation
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Object detection models have become the current tool of choice for plant disease detection in precision agriculture. Most existing research improves the performance by ameliorating networks and optimizing the loss function. However, the data-centric part of a whole project also needs more investigation. In this paper, we proposed a systematic strategy with three different annotation methods for plant disease detection: local, semi-global, and global label. Experimental results on our paprika disease dataset show that a single class annotation with semi-global boxes may improve accuracy. In addition, we also studied the noise factor during the labeling process. An ablation study shows that annotation noise within 10% is acceptable for keeping good performance. Overall, this data-centric numerical analysis helps us to understand the significance of annotation methods, which provides practitioners a way to obtain higher performance and reduce annotation costs on plant disease detection tasks. Our work encourages researchers to pay more attention to label quality and the essential issues of labeling methods.
Abstract
Object detection models have become the current tool of choice for plant disease detection in precision agriculture. Most existing research improves the performance by ameliorating networks and optimizing the loss function. However, the data-centric part of a whole project also needs more investigation. In this paper, we proposed a systematic strategy with three different annotation methods for plant disease detection: local, semi-global, and global label. Experimental results on our paprika disease dataset show that a single class annotation with semi-global boxes may improve accuracy. In addition, we also studied the noise factor during the labeling process. An ablation study shows that annotation noise within 10% is acceptable for keeping good performance. Overall, this data-centric numerical analysis helps us to understand the significance of annotation methods, which provides practitioners a way to obtain higher performance and reduce annotation costs on plant disease detection tasks. Our work encourages researchers to pay more attention to label quality and the essential issues of labeling methods.
참고문헌 (17)
- Saleem M H, "Plant disease detection and classification by deep learning", Plants, 8(11), pp.468~ (2019)
- Vishnoi V K, "Plant disease detection using computational intelligence and image processing", Journal of Plant Diseases and Protection, 128(1), pp.19~53 (2021)
- Ferentinos K P, "Deep learning models for plant disease detection and diagnosis", Computers and electronics in agriculture, 145, pp.311~318 (2018)
- Fuentes A, "A robust deeplearning-based detector for real-time tomato plant diseases and pests recognition", Sensors, 17(9) (2017)
- Fuentes A, "Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques", Frontiers in plant science (2021)
- Fuentes A F, "High-performance deep neural network-based tomato plant diseases and pests diagnosis system with refinement filter bank", Frontiers in plant science (2018)
- Nazki H, "Unsupervised image translation using adversarial networks for improved plant disease recognition", Computers and Electronics in Agriculture, 168 (2020)
- Gao, F, "Multiclass fruit-on-plant detection for apple in SNAP system using Faster R-CNN", Computers and Electronics in Agriculture, 176 (2020)
- Schauberger, B, "A systematic review of local to regional yield forecasting approaches and frequently used data resources", European Journal of Agronomy, 120 (2020)
- Emmi, L, "A hybrid representation of the environment to improve autonomous navigation of mobile robots in agriculture", Precision Agriculture, 22, pp.524~549 (2021)
- Chen, Y, "Real-time 3D unstructured environment reconstruction utilizing VR and Kinect-based immersive teleoperation for agricultural field robots", Computers and Electronics in Agriculture, 175 (2020)
- Li Y, "Toward sustainability : trade-off between data quality and quantity in crop pest recognition", Frontiers in plant science (2021)
- Tan M, "Efficientnet : Rethinking model scaling for convolutional neural networks", Proceedings of the 36th International Conference on Machine Learning, PMLR, pp.6105~6114 (2019)
- Tan M, "Efficientnetv2 : Smaller models and faster training", Proceedings of the 38th International Conference on Machine Learning, PMLR, pp.10096~10106 (2021)
- Liu Z, "Swin Transformer V2 : Scaling Up Capacity and Resolution", arXiv preprint arXiv : 2111. 09883, ~ (2021)
- Wang X A, "Data-centric analysis of on-tree fruit detection : Experiments with deep learning", Computers and Electronics in Agriculture, 194 (2022)
- Liu X, "Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation", arXiv preprint arXiv : 2203. 03810, ~ (2022)