相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Information Systems
Xuewei Chao et al.
Summary: In this study, a novel data augmentation method called H-SMOTE is proposed to solve the few-shot imbalanced classification problem. Extensive experiments show that H-SMOTE outperforms the traditional SMOTE method in multiple evaluation metrics, and the augmented data distribution by H-SMOTE is more uniform and stable.
MULTIMEDIA SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yue Yang et al.
Summary: In this paper, a sample selection method based on few-shot learning is proposed, which is verified to be effective through target type recognition test. Compared with random selection method, it can improve the accuracy by 4-10% in different time lengths.
MULTIMEDIA SYSTEMS
(2023)
Article
Telecommunications
Yang Li et al.
Summary: The ongoing data explosion has posed unprecedented challenges to the information security of communication networks. This study focuses on the data redundancy analysis and screening of images, which are commonly used as information transmission carriers. Through extensive experiments, it is found that open datasets from different domains exhibit serious data redundancy. A novel entropy-based information screening method is proposed, outperforming random sampling under various experimental conditions.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Agronomy
Xiaojun Jin et al.
Summary: This paper presents a novel deep-learning-based method for weed detection in vegetable fields. By recognizing vegetable crops and classifying other green objects as weeds, rapid and accurate weed control can be achieved. The experimental results show that this method has an accuracy above 97% in the testing dataset, with YOLO-v3 model performing the best.
PEST MANAGEMENT SCIENCE
(2022)
Article
Plant Sciences
Yang Li et al.
Summary: Smart agriculture relies on high-quality data for improved efficiency and reduced costs. However, current research on image quality assessment ignores crucial information aspects. This study proposes an effective distance-entropy indicator to differentiate good and bad data, with comparative experiments demonstrating its validity and stability.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Agronomy
Di Zhang et al.
Summary: This paper proposes a detection framework for locating chili seedling crops in large-field UAV images based on few-shot learning. By slicing crop images into subcategories and using a prototypical network, the method overcomes the difficulties of locating similar objects on a small scale. The detection process utilizes a clustering superpixel segmentation method to generate candidate regions and a prototypical network for recognizing patch images. Experimental results show a location accuracy of 96.46% for chili seedling crops.
Article
Computer Science, Information Systems
Yang Li et al.
Summary: From the perspective of information value, a simple and effective approach called disturbed-entropy is proposed to assess data quality. The existing samples per category in image classification task are statistically represented as a pixel prototype, which is used to disturb the unseen samples. Then, the entropy of disturbed image is calculated based on predicted probability. Numerical and visual experiments are conducted to show the effectiveness of the approach.
Article
Automation & Control Systems
Jiachen Yang et al.
Summary: This article introduces an effective blind quality evaluation metric for screen content images using stacked autoencoders. Experimental results demonstrate that the proposed method outperforms existing blind image quality assessment metrics on two public databases.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Electrical & Electronic
Jiachen Yang et al.
Summary: This paper introduces a new deep forgery detection method called MSTA-Net, which effectively tracks and corrects deep forgery by simulating the forgery trace in the process of image generation, using self-texture attention mechanism and probability tuple loss function. Experiments show that the proposed method performs well on forgery databases and reaches the state-of-the-art.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Agriculture, Multidisciplinary
Wan-Soo Kim et al.
Summary: In this study, a few-shot learning-based effective segmentation method for tilled soil regions is proposed, which can detect tilled soil regions and provide tillage path guidance for autonomous tractors. By utilizing image patch classification and one-shot classification model design, the tilled and non-tilled soil can be distinguished, and the tilled soil region can be segmented by clustering corresponding image patches.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Agriculture, Multidisciplinary
Yang Li et al.
Summary: This study is the first work of task-driven meta-learning few-shot classification in the field of agriculture, providing a significant reference and benchmark comparison for follow-up studies in the agricultural field by assembling a comprehensive dataset and conducting multiple comparison experiments.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Biochemical Research Methods
Xihuizi Liang
Summary: This study proposes a few-shot learning framework for classifying cotton leaf disease spots, which can help prevent and control cotton diseases. By comparing SVM and threshold segmentation methods, it is found that SVM retains more information of leaf spots for better classification. The study also demonstrates that DenseNet with SSO achieves the highest classification accuracy compared to other neural networks.
Article
Plant Sciences
Yang Li et al.
Summary: In the field of intelligent plant protection, the method of embedding range judgment can achieve the same recognition performance as all data with a small amount of high-quality data, and limited good data can outperform a large amount of bad data.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Agriculture, Multidisciplinary
Chunshan Wang et al.
Summary: This paper proposes a small-sample recognition model of vegetable diseases in complex backgrounds based on image text collaborative representation learning (ITC-Net), which achieves good results. The model combines disease image modal information with disease text modal information, effectively utilizing the correlation and complementarity between the two types of disease information.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Review
Agriculture, Multidisciplinary
A. S. M. Mahmudul Hasan et al.
Summary: The rapid development of deep learning techniques has enabled efficient detection and classification of objects from images or videos, with applications in agriculture especially for weed management. Automated weed detection plays a key role in improving crop yields and fine-tuning pre-trained models on plant datasets has proven to achieve high accuracy.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Agriculture, Multidisciplinary
Lin Li et al.
Summary: This paper proposes a Siamese domain transfer network (SDTN) architecture to transfer convolution features for maize residue segmentation using an intermediate domain and knowledge transfer through convolution layers. Experimental results demonstrate that the method can effectively transfer features and achieve a lower segmentation error rate.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Engineering, Electrical & Electronic
Jiachen Yang et al.
Summary: This paper proposes a coding-based sequence preprocessing method that effectively improves the effect of Deep Learning in target recognition. Additionally, using a neural network to estimate micro-motion parameters of UAV enhances the ability to recognize targets using micro-motion information.
PHYSICAL COMMUNICATION
(2021)
Article
Computer Science, Theory & Methods
Jiachen Yang et al.
Summary: With the rapid development of face manipulation technology, Convolutional Neural Network (CNN) discriminators have high accuracy in identifying fake/real face images. Multi-scale texture difference information plays a crucial role in face forgery detection. The proposed MTD-Net model, leveraging CDC and ASPP, outperforms existing approaches in robust face forgery detection.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Article
Agriculture, Multidisciplinary
Yang Li et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Agriculture, Multidisciplinary
David Argueso et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Computer Science, Artificial Intelligence
S. Hernandez et al.
APPLIED SOFT COMPUTING
(2020)
Article
Agronomy
Yang Li et al.
Article
Computer Science, Hardware & Architecture
Ian Goodfellow et al.
COMMUNICATIONS OF THE ACM
(2020)
Article
Agriculture, Multidisciplinary
Fangming Zhong et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Agriculture, Multidisciplinary
Yang Li et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Engineering, Electrical & Electronic
Azam Karami et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2020)
Article
Genetics & Heredity
Osval A. Montesinos-Lopez et al.
G3-GENES GENOMES GENETICS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Muhammad Abdullah Jamal et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Amit Alfassy et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Agriculture, Multidisciplinary
L. C. Uzal et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2018)
Article
Biochemical Research Methods
Mohammed Albaqami et al.
Article
Agricultural Engineering
Yu Sun et al.
BIOSYSTEMS ENGINEERING
(2018)
Article
Agriculture, Multidisciplinary
Xi Cheng et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2017)
Article
Agriculture, Multidisciplinary
Keun Ha Choi et al.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2015)
Article
Multidisciplinary Sciences
Brenden M. Lake et al.
Article
Biochemical Research Methods
Jian-Feng Li et al.
