Article
Computer Science, Artificial Intelligence
Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu
Summary: This paper provides a comprehensive survey on deep semi-supervised learning methods, including model design and unsupervised loss functions. It categorizes existing methods into different types and reviews 60 representative methods with a detailed comparison. The paper also discusses the shortcomings of existing methods and proposes heuristic solutions.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Chih-Shen Cheng, Amir H. Behzadan, Arash Noshadravan
Summary: This study improves post-disaster preliminary damage assessment using a stacked convolutional neural network trained on UAV imagery from Hurricane Dorian. The model achieves high building localization precision and classification accuracy, with a positive accuracy-confidence correlation for situations where ground-truth information is not readily available. The relationship between building size, number of stories, and disaster damage severity is also examined for damage assessment comparison.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2021)
Article
Geosciences, Multidisciplinary
Polina Berezina, Desheng Liu
Summary: This article proposes a deep learning-based model for damage assessment in the wake of hurricanes, using remote sensing and large-scale satellite imagery dataset. The study finds that this open-source deep learning workflow has better applicability in hurricane management and recovery, and can be integrated into emergency response frameworks for automated damage assessment and prioritization of relief efforts.
GEOMATICS NATURAL HAZARDS & RISK
(2022)
Article
Mathematics
Xiaodan Zhang, Xun Zhang, Yuan Xiao, Gang Liu
Summary: Image aesthetic quality assessment is widely used in various applications, but existing methods require excessive labeled data. This study proposes a theme-aware semi-supervised method to address this issue, achieving comparable performance with fully supervised learning. This method consists of a representation learning step and a label propagation step.
Article
Computer Science, Artificial Intelligence
Qian Gui, Hong Zhou, Na Guo, Baoning Niu
Summary: Semi-supervised learning (SSL) improves deep neural network performance by utilizing unlabeled data when labeled data is scarce. However, state-of-the-art SSL algorithms assume balanced class distributions between labeled and unlabeled datasets, making them ineffective for imbalanced training data. Recent research has explored methods to mitigate the degradation of semi-supervised learning models in class-imbalanced scenarios.
Article
Biology
Lei Su, Yu Liu, Minghui Wang, Ao Li
Summary: This study proposes a novel semi-supervised deep learning method called Semi-HIC for histopathological image classification. By introducing a new semi-supervised loss function and employing an efficient network architecture, the method effectively addresses the challenges of inter-class similarity and intra-class variation in histopathological images, leading to significantly improved classification performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Environmental Sciences
Brandon Hobley, Riccardo Arosio, Geoffrey French, Julie Bremner, Tony Dolphin, Michal Mackiewicz
Summary: Intertidal seagrass plays a vital role in coastal environments, but most habitats have been declining due to human impacts. This study compares two methods for classifying seagrass habitats- OBIA and FCNNs. Using semi-supervision, we demonstrate the utility of FCNNs in mapping seagrass and other coastal features.
Article
Computer Science, Artificial Intelligence
Sridhar Mandapati, Seifedine Kadry, R. Lakshmana Kumar, Krongkarn Sutham, Orawit Thinnukool
Summary: Several deep learning architectures with feature learning have been proposed for image processing, data interpretation, speech recognition, and video analysis. This paper presents DLM-SSC, a unique method that combines high-order convolution and feature learning for semi-supervised node classification tasks. The suggested approaches outperform similar algorithms in terms of efficiency and effectiveness, as demonstrated on citation datasets and other datasets.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Agriculture, Dairy & Animal Science
Mustafa Jaihuni, Hao Gan, Tom Tabler, Maria Prado, Hairong Qi, Yang Zhao
Summary: The researchers used a combination of artificial intelligence methods and computer algorithms to track individual chickens, which provided more accurate measurements of their mobility compared to traditional methods. This combined model could provide real-time and accurate information.
Article
Chemistry, Analytical
Bee-ing Sae-ang, Wuttipong Kumwilaisak, Pakorn Kaewtrakulpong
Summary: The study proposed a semi-supervised approach that utilized both unlabeled and labeled samples to automatically segment out defect regions through network training. Experimental results showed a 3.83% overall improvement with the help of a handful of ground-truth segmentation maps.
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu
Summary: Supervised deep learning methods require large labeled datasets for accurate medical image segmentation. This paper proposes a local contrastive loss-based approach that utilizes pseudo-labels of unlabeled images and limited annotated images to learn pixel-level features for segmentation. Experimental results on three public medical datasets demonstrate the substantial improvement achieved by the proposed method.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Information Systems
Roohallah Alizadehsani, Danial Sharifrazi, Navid Hoseini Izadi, Javad Hassannataj Joloudari, Afshin Shoeibi, Juan M. Gorriz, Sadiq Hussain, Juan E. Arco, Zahra Alizadeh Sani, Fahime Khozeimeh, Abbas Khosravi, Saeid Nahavandi, Sheikh Mohammed Shariful Islam, U. Rajendra Acharya
Summary: This article introduces a semi-supervised classification method using limited labeled data, relying on Sobel edge detection and Generative Adversarial Networks (GANs) to automate COVID-19 diagnosis. Experimental results demonstrate that the proposed method significantly outperforms supervised learning methods in cases where labeled data is scarce.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Jui-Hung Chang, Hsiu-Chen Weng
Summary: Semi-supervised learning utilizes a large amount of unlabeled data to improve training results and reduce noise. This study proposes AC and OS algorithms to guide the model's attention to classified features and improve efficiency and performance of model learning.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Biology
Wenxue Li, Wei Lu, Jinghui Chu, Qi Tian, Fugui Fan
Summary: In this paper, a novel Confidence-Guided Mask Learning (CGML) method is proposed for semi-supervised medical image segmentation. The method introduces an auxiliary generation task with mask learning and a confidence-guided masking strategy to improve segmentation accuracy and feature representation reliability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Lars Schmarje, Monty Santarossa, Simon-Martin Schroeder, Reinhard Koch
Summary: Current deep learning strategies in computer vision are highly dependent on labeled data, which may not be feasible for many real-world problems. Therefore, incorporating unlabeled data and addressing issues like class imbalance and robustness is crucial. Future research trends include scalability, decreasing supervision needs, and combining ideas from different methods for improved performance.
Article
Engineering, Civil
Shi Ye, Xiangang Lai, Ivan Bartoli, A. Emin Aktan
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Christian J. Mahoney, Katie Jensen, Fusheng Wei, Haozhen Zhao, Han Qin, Shi Ye
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Robert Keeling, Rishi Chhatwal, Nathaniel Huber-Fliflet, Jianping Zhang, Fusheng Wei, Haozhen Zhao, Ye Shi, Han Qin
2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Nathaniel Huber-fliflet, Fusheng Wei, Haozhen Zhao, Han Qin, Shi Ye, Amy Tsang
2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Fusheng Wei, Han Qin, Shi Ye, Haozhen Zhao
2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Christian J. Mahoney, Nathaniel Huber-Fliflet, Katie Jensen, Haozhen Zhao, Robert Neary, Shi Ye
2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2018)
Proceedings Paper
Engineering, Civil
Emin Aktan, Ivan Bartoli, Franklin Moon, Marcello Balduccini, Kurt Sjoblom, Antonios Kontsos, Hoda Azari, Matteo Mazzotti, John Braley, Charles Young, Shi Ye, Andrew Ellenberg
EXPERIMENTAL VIBRATION ANALYSIS FOR CIVIL STRUCTURES: TESTING, SENSING, MONITORING, AND CONTROL
(2018)