A framework-based transformer and knowledge distillation for interior style classification

Review Automation & Control Systems

Smart farming using artificial intelligence: A review

Yaganteeswarudu Akkem et al.

Summary: Smart farming with artificial intelligence provides an efficient solution to today's agricultural sustainability challenges. Machine learning, deep learning, and time series analysis are essential in selecting crops, predicting yield, managing water, and forecasting demand and commodity prices. This article thoroughly reviews the application of machine learning and deep learning techniques in the agriculture industry, highlighting the importance of crop selection and production forecasting. By using time series analysis and estimating crop yield, appropriate crop recommendations can be suggested, addressing future food insufficiency.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Cross-modal transformer with language query for referring image segmentation

Wenjing Zhang et al.

Summary: A cross-modal transformer with language queries is proposed for referring image segmentation, which enables deep interaction between vision and language and improves the accuracy of segmentation.

NEUROCOMPUTING (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Boosting R-CNN: Reweighting R-CNN samples by RPN?s error for underwater object detection

Pinhao Song et al.

Summary: This work proposes a two-stage underwater object detector called boosting R-CNN, which addresses the challenges of complicated underwater environments. It includes uncertainty modeling and hard example mining, and consists of three key components: RetinaRPN, probabilistic inference pipeline, and boosting reweighting. Experimental results demonstrate the effectiveness and robustness of this method.

NEUROCOMPUTING (2023)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis

Fatemeh Haghighi et al.

Summary: This study presents a framework called DiRA that combines discriminative, restorative, and adversarial learning for self-supervised learning in computer vision and medical imaging. The experiments show that DiRA produces more generalizable representation, reduces annotation cost, and improves lesion localization accuracy.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Detection of tuberculosis from chest X-ray images: Boosting the performance with vision transformer and transfer learning

Linh T. Duong et al.

Summary: This study aims to early detect tuberculosis using medical imaging and artificial intelligence technology, proposing a solution for detecting tuberculosis from chest X-ray images and utilizing various deep neural network techniques, achieving better performance compared to existing methods.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Article Engineering, Environmental

Recycling waste classification using optimized convolutional neural network

Wei-Lung Mao et al.

Summary: This study discussed the application of an automatic classification robot based on image recognition in recycling tasks, optimizing the fully-connected layer of DenseNet121 to improve waste classification accuracy, and utilizing genetic algorithms for optimization. Results showed that the optimized DenseNet121 achieved a highest accuracy of 99.6% on TrashNet, outperforming other studies' CNNs.

RESOURCES CONSERVATION AND RECYCLING (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary