Maize residue segmentation using Siamese domain transfer network

Li, Lin; Li, Jia; Lv, Chengxu; Yuan, Yazhou; Zhao, Bo

doi:10.1016/j.compag.2021.106261

Cited by 8 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the deep learning field, domain transferwhich is defined as the process of moving data from one domain to another by finding commonalities and creating connections between them-has attracted a lot of interest [26]. This approach proves instrumental in addressing challenges such as image/scene discrepancies during both training and practical application, allowing for the modification of specific data features while preserving others [27].…”

Section: Literature Reviewmentioning

confidence: 99%

Augmented Image Dataset Using Image-to-Image Translation to Enhance the Non-Hodgkin Lymphoma Diagnosis

Zerari,

Khelil,

Djerou

et al. 2024

RIA

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Augmented Image Dataset Using Image-to-Image Translation to Enhance the Non-Hodgkin Lymphoma Diagnosis

Zerari,

Khelil,

Djerou

et al. 2024

RIA

View full text Add to dashboard Cite

“…To address this problem, Li et al. (2021) propose a metric‐based learning method that requires only a limited number of samples for the maize residue detection task. This approach, in particular, adopts the intermediate domain to aid in the migration of meta‐knowledge from the source domain to the maize residue segmentation, achieving improved accuracy of maize residue detection tasks using a small number of labeled samples to provide effective guidance for conservation tillage.…”

Section: Applications Of Meta‐learning In Plant Disease Recognitionmentioning

confidence: 99%

Meta‐learning shows great potential in plant disease recognition under few available samples

Deng

Wang

et al. 2023

The Plant Journal

View full text Add to dashboard Cite

Plant diseases worsen the threat of food shortage with the growing global population, and disease recognition is the basis for the effective prevention and control of plant diseases. Deep learning has made significant breakthroughs in the field of plant disease recognition. Compared with traditional deep learning, metalearning can still maintain more than 90% accuracy in disease recognition with small samples. However, there is no comprehensive review on the application of meta-learning in plant disease recognition. Here, we mainly summarize the functions, advantages, and limitations of meta-learning research methods and their applications for plant disease recognition with a few data scenarios. Finally, we outline several research avenues for utilizing current and future meta-learning in plant science. This review may help plant science researchers obtain faster, more accurate, and more credible solutions through deep learning with fewer labeled samples.

show abstract

“…The detection of crops can effectively perceive the position of crops, soil and so on, and help farmers automatically monitor farmland. Specifically, [60]. The application of few-shot learning enables people to control the quality of crops with the least resources.…”

Section: Crop Detectionmentioning

confidence: 99%

“…The detection of crops can effectively perceive the position of crops, soil and so on, and help farmers automatically monitor farmland. Specifically, Zhang et al used UAV technology and few-shot learning to detect the position of crop seeds [ 58 ], Kim et al used few-shot learning to detect the cultivated soil area in the two-dimensional perspective scene to provide farming path guidance for automatic tractors [ 59 ], and Li et al proposed a Siamese domain transfer network (SDTN) structure to detect corn residues [ 60 ]. The application of few-shot learning enables people to control the quality of crops with the least resources.…”

Section: Applicationsmentioning

confidence: 99%

A survey of few-shot learning in smart agriculture: developments, applications, and challenges

Yang

Guo

et al. 2022

Plant Methods

View full text Add to dashboard Cite

With the rise of artificial intelligence, deep learning is gradually applied to the field of agriculture and plant science. However, the excellent performance of deep learning needs to be established on massive numbers of samples. In the field of plant science and biology, it is not easy to obtain a large amount of labeled data. The emergence of few-shot learning solves this problem. It imitates the ability of humans’ rapid learning and can learn a new task with only a small number of labeled samples, which greatly reduces the time cost and financial resources. At present, the advanced few-shot learning methods are mainly divided into four categories based on: data augmentation, metric learning, external memory, and parameter optimization, solving the over-fitting problem from different viewpoints. This review comprehensively expounds on few-shot learning in smart agriculture, introduces the definition of few-shot learning, four kinds of learning methods, the publicly available datasets for few-shot learning, various applications in smart agriculture, and the challenges in smart agriculture in future development.

show abstract

Maize residue segmentation using Siamese domain transfer network

Cited by 8 publications

References 11 publications

Augmented Image Dataset Using Image-to-Image Translation to Enhance the Non-Hodgkin Lymphoma Diagnosis

Augmented Image Dataset Using Image-to-Image Translation to Enhance the Non-Hodgkin Lymphoma Diagnosis

Meta‐learning shows great potential in plant disease recognition under few available samples

A survey of few-shot learning in smart agriculture: developments, applications, and challenges

Contact Info

Product

Resources

About