Novel Category Discovery in Plant Species and Disease Identification through Knowledge Distillation
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.
Abstract
Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.
참고문헌 (19)
- Dong, J., "Towards Improved Performance on Plant Disease Recognition with Symptoms Specific Annotation", Smart Media Journal, 11(4), pp.38~45 (2022)
- Dong, J., "Data-centric annotation analysis for plant disease detection:Strategy, consistency, and performance", Frontiers in Plant Science, 13 (2022)
- Dong, J., "A new deep learningbased dynamic paradigm towards open-world plant disease detection", Frontiers in Plant Science, 14 (2023)
- Dong, J., "An iterative noisy annotation correction model for robust plant disease detection", Frontiers in Plant Science, 14 (2023)
- Dong, J., "Towards Improved Performance on Plant Disease Recognition with Symptoms Specific Annotation", Smart Media Journal, 11(4), pp.38~45 (2022)
- Xu, M., "Unsupervised transfer learning for plant anomaly recognition", Smart Media Journal, 11(4), pp.30~37 (2022)
- Xu, M., "Predicting Desired Fertigation for Rose Using Internet of Things Sensors and Time-Series Model", Smart Media Journal, 13(2), pp.16~22 (2024)
- Zhong, Z., "Neighborhood contrastive learning for novel class discovery", Proceedings of the Proceedings of the IEEE, 2021, 10867~10875
- Cui, P., "Out-of-distribution(ood)detection based on deep learning : A review", Electronics, 11(21) (2022)
- Meng, Y., "Known and unknown class recognition on plant species and diseases", Computers and Electronics in Agriculture, 215 (2023)
- Fuentes, A., "Open set self and across domain adaptation for tomato disease recognition with deep learning techniques", Frontiers in Plant Science, 12 (2021)
- Gou, J., "Knowledge distillation : A survey", International Journal of Computer Vision, 129, pp.1789~1819 (2021)
- Caron, M., "Emerging properties in self-supervised vision transformers", Proceedings of the Proceedings of the IEEE, 2021, 9650~9660
- Fini, E., "A unified objective for novel class discovery", Proceedings of the Proceedings of the IEEE, 2021, 9284~9292
- Gu, P., "Class-relation knowledge distillation for novel class discovery" (2023), lamp
- Kuhn, H. W, "The Hungarian method for the assignment problem", Naval research logistics quarterly, 2(1-2), pp.83~97 (1955)