Cargando…
Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning
Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to collect. Consequently, the practical application of current deep...
Autores principales: | Xu, Mingle, Kim, Hyongsuk, Yang, Jucheng, Fuentes, Alvaro, Meng, Yao, Yoon, Sook, Kim, Taehyun, Park, Dong Sun |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10557492/ https://www.ncbi.nlm.nih.gov/pubmed/37810377 http://dx.doi.org/10.3389/fpls.2023.1225409 |
Ejemplares similares
-
Style-Consistent Image Translation: A Novel Data Augmentation Paradigm to Improve Plant Disease Recognition
por: Xu, Mingle, et al.
Publicado: (2022) -
Open Set Self and Across Domain Adaptation for Tomato Disease Recognition With Deep Learning Techniques
por: Fuentes, Alvaro, et al.
Publicado: (2021) -
A New Deep Learning-based Dynamic Paradigm Towards Open-World Plant Disease Detection
por: Dong, Jiuqing, et al.
Publicado: (2023) -
Transfer learning for versatile plant disease recognition with limited data
por: Xu, Mingle, et al.
Publicado: (2022) -
An iterative noisy annotation correction model for robust plant disease detection
por: Dong, Jiuqing, et al.
Publicado: (2023)