Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Honggang Chen et al.
Summary: This study proposes a self-supervised cycle-consistent learning-based scale-arbitrary super-resolution framework (SCL-SASR) for real-world images. The framework includes a Scale-Arbitrary Super-Resolution Network (SASRN) and an inverse Scale-Arbitrary Resolution-Degradation Network (SARDN), which ensure the adaptability to image-specific degradations and the ability to handle arbitrary scaling factors.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Manel Farhat et al.
Summary: This paper proposes a novel self-supervised approach for endoscopic image matching based on deep learning techniques. When compared to standard hand-crafted local feature descriptors, our method outperformed them in terms of precision and recall. Furthermore, our self-supervised descriptor provides a competitive performance in comparison to a selection of state-of-the-art deep learning based supervised methods in terms of precision and matching score.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Anupama Padha et al.
Summary: Long-term stress can have a significant impact on mental health, leading to various diseases. The use of modern technologies such as artificial intelligence and IOT enables effective mental health monitoring. This research aims to develop an efficient machine learning model with quantum advantages for continuous mental health monitoring. The model is achieved through three phases, involving the study of classical machine learning models, principal component analysis, and a meta-approach to combine predictive abilities. Experimental results show that the proposed model outperforms individual quantum models.
QUANTUM MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Meirong Wei et al.
Summary: In this article, a novel ResNet-based fault diagnosis method is proposed, utilizing data transformation combinations and a self-supervised learning method to achieve fault diagnoses for machines with very few samples, demonstrating superior performance and diagnostic accuracy.
Article
Computer Science, Artificial Intelligence
Johannes Poppelbaum et al.
Summary: This paper introduces a self-supervised learning approach based on contrastive learning for time-series analysis, achieving higher accuracy through novel data augmentation techniques, as validated on the Tennessee Eastman dataset.
APPLIED SOFT COMPUTING
(2022)
Article
Automation & Control Systems
Hui Zeng et al.
Summary: In this study, we propose a simple framework called SimCLRT for rumor tracking, which uses contrastive learning to alleviate the problem of tweet coverage. The experimental results show that SimCLRT has a good detection performance in different types of events, especially for events with a small number of tweets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xinyu Yang et al.
Summary: Time series data is often lacking in labels, which hinders the performance of deep learning models. Self-supervised representation learning can improve model performance by extracting information from unlabeled data. This study proposes the TimeCLR framework, combining DTW and InceptionTime, for univariate time series representation.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Physics, Multidisciplinary
Jin-Dao Tang et al.
Summary: Quantum entanglement in optomechanical systems is crucial for the advancement of quantum science and technology, serving purposes in fundamental physics exploration and quantum information processing. Despite the lack of size limitation in quantum mechanics, the experimental preparation and detection of macroscopic quantum entanglement face significant challenges. However, recent experimental progress has demonstrated non-local correlation and entanglement among mechanical oscillators and between oscillators and electromagnetic fields, paving the way for further developments.
Article
Computer Science, Artificial Intelligence
Kihwan Choi et al.
Summary: This study proposes a self-supervised learning approach to train a CNN denoiser with LDCT images alone, avoiding unnecessary radiation exposure. Results show that this method performs equally well as traditional supervised learning models in terms of denoising performance and clinical evaluation.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Quantum Science & Technology
B. Jaderberg et al.
Summary: The resurgence of self-supervised learning offers a scalable solution for handling large datasets without human annotation. This study explores the potential of quantum neural networks (QNNs) in addressing hardware limitations and providing more powerful architectures, demonstrating the advantages of small-scale QNN in visual representation learning and the comparable accuracy of current noisy devices to classical models for image classification on downstream tasks.
QUANTUM SCIENCE AND TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Duc Hoang Tran et al.
Summary: This paper proposes an anomaly detection method using a self-supervised learning framework in a time-series dataset, which improves the model performance in terms of high accuracy and lightweight method. Experimental results indicate that this method outperforms classic anomaly detection methods, and the efficiency of the self-supervised learning method for time-series anomaly detection is demonstrated in a real testbed.
Article
Computer Science, Artificial Intelligence
Ruoyu Wu et al.
Summary: Lung cancer is a fatal malignant disease that poses a serious threat to human health and life. In the screening of lung cancer, accurate identification of lung nodules is crucial. This study proposes a new self-supervised transfer learning framework that effectively reduces the dependence on labeled samples by exploring valuable information from unlabeled CT scans, achieving benign-malignant identification of nodules on chest CT.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Alvaro S. Hervella et al.
Summary: This study proposes a self-supervised learning method using unlabeled multimodal data to enhance the accuracy of retinal computer-aided diagnosis systems, without relying on manual annotation. Experimental results demonstrate satisfactory performance in diagnosing different ocular diseases, showcasing the potential of leveraging unlabeled multimodal visual data in the medical field.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Longlong Jing et al.
Summary: This paper reviews deep learning-based self-supervised general visual feature learning methods, covering motivation, pipeline, architectures, schema, evaluation metrics, datasets, performance comparisons, and future directions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Haocong Rao et al.
Summary: The paper proposes a contrastive action learning paradigm named AS-CAL, which learns action representations in an unsupervised manner by contrasting similarities between augmented instances of skeleton sequences and encoding longterm action dynamics using momentum LSTM. The approach significantly outperforms hand-crafted methods and even achieves superior performance to many supervised learning methods.
INFORMATION SCIENCES
(2021)
Proceedings Paper
Audiology & Speech-Language Pathology
Dongwei Jiang et al.
Summary: Self-supervised visual pretraining method SimCLR has made significant progress on ImageNet and inspired the development of Speech SimCLR for speech representation learning. By combining data augmentation and loss functions, Speech SimCLR achieves competitive results in speech emotion recognition and speech recognition tasks.
Review
Engineering, Multidisciplinary
Ashish Jaiswal et al.
Summary: Self-supervised learning, particularly through contrastive learning, has gained popularity for its cost-effective approach in using self-defined pseudolabels for various downstream tasks. This paper extensively reviews self-supervised methods following the contrastive approach, explaining pretext tasks and different architectures used. Performance comparisons across multiple downstream tasks demonstrate variations in method effectiveness.
Article
Multidisciplinary Sciences
Kerstin Beer et al.
NATURE COMMUNICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Debanjan Konar et al.
APPLIED SOFT COMPUTING
(2020)
Article
Computer Science, Artificial Intelligence
Alvaro S. Hervella et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Physics, Multidisciplinary
Shivani Saini et al.
INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS
(2020)
Article
Physics, Multidisciplinary
Iris Cong et al.
Article
Computer Science, Theory & Methods
Connor Shorten et al.
JOURNAL OF BIG DATA
(2019)
Review
Computer Science, Information Systems
Enrique Garcia-Ceja et al.
PERVASIVE AND MOBILE COMPUTING
(2018)
Review
Psychiatry
Amy M. Kilbourne et al.
CANADIAN JOURNAL OF PSYCHIATRY-REVUE CANADIENNE DE PSYCHIATRIE
(2010)
