Disturbed-entropy: A simple data quality assessment approach

Article Agriculture, Multidisciplinary

Fast and accurate detection of kiwifruit in orchard using improved YOLOv3-tiny model

Longsheng Fu et al.

Summary: Automatic detection of kiwifruit in the orchard is challenging due to varying illumination and color similarity with the complex background. A deep YOLOv3-tiny model (DY3TNet) was developed for efficient and accurate detection, achieving high precision and fast processing speed, especially in images captured with flash.

PRECISION AGRICULTURE (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Meta-learning baselines and database for few-shot classification in agriculture

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)

添加到收藏夹

Article Plant Sciences

Toward Sustainability: Trade-Off Between Data Quality and Quantity in Crop Pest Recognition

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)

添加到收藏夹

Article Biochemical Research Methods

Semi-supervised few-shot learning approach for plant diseases recognition

Yang Li et al.

Summary: The proposed semi-supervised few-shot learning approach in this study demonstrates effectiveness and generalization in plant leaf disease recognition, outperforming other related works with fewer labeled training data. The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%.

PLANT METHODS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

No-Reference Quality Assessment for Screen Content Images Using Visual Edge Model and AdaBoosting Neural Network

Jiachen Yang et al.

Summary: This paper proposes a competitive no-reference metric to assess the perceptive quality of screen content images (SCIs) using human visual edge model and AdaBoosting neural network. The method computes multi-scale edge maps via the DOG operator, estimates and fits their DOG coefficients for edge features, and uses ABPNN to map quality-aware features to perceptual quality score of SCIs. The proposed method shows highly competitive performance on public SCI-oriented databases with high consistency with the human visual system.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Oncology

Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients

Jianzhu Ma et al.

Summary: The study applies few-shot learning to train a versatile neural network model for predicting drug response, which can quickly adapt to different biological contexts and identify critical molecular features.

NATURE CANCER (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary