Semi-supervised Learning Research Articles

Multi-Level Cross-Modal Interactive-Network-Based Semi-Supervised Multi-Modal Ship Classification

Ship image classification identifies the type of ships in an input image, which plays a significant role in the marine field. To enhance the ship classification performance, various research focuses on studying multi-modal ship classification, which aims at combining the advantages of visible images and infrared images to capture complementary information. However, the current methods simply concatenate features of different modalities to learn complementary information, which neglects the multi-level correlation between different modalities. Moreover, the existing methods require a large amount of labeled ship images to train the model. How to capture the multi-level cross-modal correlation between unlabeled and labeled data is still a challenge. In this paper, a novel semi-supervised multi-modal ship classification approach is proposed to solve these issues, which consists of two components, i.e., multi-level cross-modal interactive network and semi-supervised contrastive learning strategy. To learn comprehensive complementary information for classification, the multi-level cross-modal interactive network is designed to build local-level and global-level cross-modal feature correlation. Then, the semi-supervised contrastive learning strategy is employed to drive the optimization of the network with the intra-class consistency constraint based on supervision signals of unlabeled samples and prior label information. Extensive experiments on the public datasets demonstrate that our approach achieves state-of-the-art semi-supervised classification effectiveness.

Physics-informed two-tier neural network for non-linear model order reduction

AbstractIn recent years, machine learning (ML) has had a great impact in the area of non-intrusive, non-linear model order reduction (MOR). However, the offline training phase often still entails high computational costs since it requires numerous, expensive, full-order solutions as the training data. Furthermore, in state-of-the-art methods, neural networks trained by a small amount of training data cannot be expected to generalize sufficiently well, and the training phase often ignores the underlying physical information when it is applied with MOR. Moreover, state-of-the-art MOR techniques that ensure an efficient online stage, such as hyper reduction techniques, are either intrusive or entail high offline computational costs. To resolve these challenges, inspired by recent developments in physics-informed and physics-reinforced neural networks, we propose a non-intrusive, physics-informed, two-tier deep network (TTDN) method. The proposed network, in which the first tier achieves the regression of the unknown quantity of interest and the second tier rebuilds the physical constitutive law between the unknown quantities of interest and derived quantities, is trained using pretraining and semi-supervised learning strategies. To illustrate the efficiency of the proposed approach, we perform numerical experiments on challenging non-linear and non-affine problems, including multi-scale mechanics problems.

Advancing Additive Manufacturing Through Machine Learning Techniques: A State-of-the-Art Review

In the fourth industrial revolution, artificial intelligence and machine learning (ML) have increasingly been applied to manufacturing, particularly additive manufacturing (AM), to enhance processes and production. This study provides a comprehensive review of the state-of-the-art achievements in this domain, highlighting not only the widely discussed supervised learning but also the emerging applications of semi-supervised learning and reinforcement learning. These advanced ML techniques have recently gained significant attention for their potential to further optimize and automate AM processes. The review aims to offer insights into various ML technologies employed in current research projects and to promote the diverse applications of ML in AM. By exploring the latest advancements and trends, this study seeks to foster a deeper understanding of ML’s transformative role in AM, paving the way for future innovations and improvements in manufacturing practices.

Local field potential-based brain-machine interface to inhibit epileptic seizures by spinal cord electrical stimulation.

This study proposes a closed-loop brain-machine interface (BMI) based on spinal cord stimulation to inhibit epileptic seizures, applying a semi-supervised machine learning approach that learns from Local Field Potential (LFP) patterns acquired on the pre-ictal (preceding the seizure) condition.
 
Approach. LFP epochs from the hippocampus and motor cortex are band-pass filtered from 1 to 13 Hz, to obtain the time-frequency representation using the continuous Wavelet transform, and successively calculate the phase lock values (PLV). As a novelty, the Z-score-based PLV normalization using both modified k-means and Davies-Bouldin's measure for clustering is proposed here. Consequently, a generic seizure's detector is calibrated for detecting seizures on the normalized PLV, and enables the spinal cord stimulation for periods of 30 s in a closed-loop, while the BMI system detects seizure events. To calibrate the proposed BMI, a dataset with LFP signals recorded on five Wistar rats during basal state and epileptic crisis was used. The epileptic crisis was induced by injecting pentylenetetrazol (PTZ). Afterwards, two experiments without/with our BMI were carried out, inducing epileptic crisis by PTZ in Wistar rats. 

Main Results. Stronger seizure events of high LFP amplitudes and long time periods were observed in the rat, when the BMI system was not used. In contrast, short-time seizure events of relative low intensity were observed in the rat, using the proposed BMI. The proposed system detected on unseen data the synchronized seizure activity in the hippocampus and motor cortex, provided stimulation appropriately, and consequently decreased seizure symptoms. 

Significance. Low-frequency LFP signals from the hippocampus and motor cortex, and cord spinal stimulation can be used to develop accurate closed-loop BMIs for early epileptic seizures inhibition, as an alternative treatment.

Almost exact recovery in noisy semi-supervised learning

Abstract Graph-based semi-supervised learning methods combine the graph structure and labeled data to classify unlabeled data. In this work, we study the effect of a noisy oracle on classification. In particular, we derive the maximum a posteriori (MAP) estimator for clustering a degree corrected stochastic block model when a noisy oracle reveals a fraction of the labels. We then propose an algorithm derived from a continuous relaxation of the MAP, and we establish its consistency. Numerical experiments show that our approach achieves promising performance on synthetic and real data sets, even in the case of very noisy labeled data.

SSML: Semi-supervised metric learning with hard samples for hyperspectral image classification

Deep learning is widely used in hyperspectral image (HSI) classification due to its powerful learning capabilities. However, its excellent performance typically requires a large number of samples, which can be time-consuming and labor-intensive to produce. The limitation of available samples greatly constrains the model's generalization performance. To alleviate the sample pressure, we propose a semi-supervised metric learning method for HSI classification that focuses on hard samples and can obtain reliable pseudo-labels through multiscale prediction. Additionally, we employ a hard sample learning strategy for network training, which concentrates on enhancing network discrimination by adaptively optimizing intra-class and inter-class distances. Performance tests on three public datasets indicate that the proposed method surpasses other state-of-the-art methods across multiple validation metrics.

AI-driven automatic generation and rendering of game characters

Abstract. This paper provides a comprehensive review of AI-driven techniques for the automatic generation and rendering of game characters, with a particular focus on Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). GANs, using adversarial training approaches, have revolutionized character development by producing incredibly realistic and aesthetically pleasing gaming characters. VAEs, despite frequently encountering issues like image blurriness, provide an alternate strategy that emphasizes diversity and originality in the generated content. Additionally, conditional models that enable more individualized and regulated character generation are explored, as well as hybrid models that combine the best features of both GANs and VAEs. The difficulties with mode collapse in GANs and the requirement for big datasets for both GANs and VAEs are also covered, along with some possible fixes like transfer learning and semi-supervised learning strategies. This analysis emphasizes the growing significance of AI-driven game character generation in the gaming industry by highlighting its current state, problems, and future directions.

Automatic delineation of cervical cancer target volumes in small samples based on multi-decoder and semi-supervised learning and clinical application

Radiotherapy has been demonstrated to be one of the most significant treatments for cervical cancer, during which accurate and efficient delineation of target volumes is critical. To alleviate the data demand of deep learning and promote the establishment and promotion of auto-segmentation models in small and medium-sized oncology departments and single centres, we proposed an auto-segmentation algorithm to determine the cervical cancer target volume in small samples based on multi-decoder and semi-supervised learning (MDSSL), and we evaluated the accuracy via an independent test cohort. In this study, we retrospectively collected computed tomography (CT) datasets from 71 pelvic cervical cancer patients, and a 3:4 ratio was used for the training and testing sets. The clinical target volumes (CTVs) of the primary tumour area (CTV1) and pelvic lymph drainage area (CTV2) were delineated. For definitive radiotherapy (dRT), the primary gross target volume (GTVp) was simultaneously delineated. According to the data characteristics for small samples, the MDSSL network structure based on 3D U-Net was established to train the model by combining clinical anatomical information, which was compared with other segmentation methods, including supervised learning (SL) and transfer learning (TL). The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) were used to evaluate the segmentation performance. The ability of the segmentation algorithm to improve the efficiency of online adaptive radiation therapy (ART) was assessed via geometric indicators and a subjective evaluation of radiation oncologists (ROs) in prospective clinical applications. Compared with the SL model and TL model, the proposed MDSSL model displayed the best DSC, HD95 and ASD overall, especially for the GTVp of dRT. We calculated the above geometric indicators in the range of the ground truth (head-foot direction). In the test set, the DSC, HD95 and ASD of the MDSSL model were 0.80/5.85 mm/0.95 mm for CTV1 of post-operative radiotherapy (pRT), 0.84/ 4.88 mm/0.73 mm for CTV2 of pRT, 0.84/6.58 mm/0.89 mm for GTVp of dRT, 0.85/5.36 mm/1.35 mm for CTV1 of dRT, and 0.84/4.09 mm/0.73 mm for CTV2 of dRT, respectively. In a prospective clinical study of online ART, the target volume modification time (MTime) was 3–5 min for dRT and 2–4 min for pRT, and the main duration of CTV1 modification was approximately 2 min. The introduction of the MDSSL method successfully improved the accuracy of auto-segmentation for the cervical cancer target volume in small samples, showed good consistency with RO delineation and satisfied clinical requirements. In this prospective online ART study, the application of the segmentation model was demonstrated to be useful for reducing the target volume delineation time and improving the efficiency of the online ART workflow, which can contribute to the development and promotion of cervical cancer online ART.

A novel method for assessment rooftop PV potential based on remote sensing images

The assessment of rooftop photovoltaic (PV) potential is highly significant for energy policy formulation. With the rapid development of computer vision (CV) and remote sensing imagery, utilizing CV to extract rooftop information is an ideal approach. However, deep learning requires a large amount of accurately annotated data, and annotating remote sensing images is a labor-intensive task. This limitation hinders the application of deep learning in rooftop PV potential assessment. To address this issue, this paper proposes a semi-supervised learning (SSL)-based segmentation model to extract rooftop information from remote sensing images. Subsequently, a rooftop classification method is proposed to categorize rooftops into several classes and estimate their rooftop PV available area ratios. Finally, the total available rooftop PV area in urban areas is evaluated, and the potential rooftop PV installed capacity and power generation are calculated. This method is applied in the Longhu District of Shantou City, Guangdong Province. The evaluation results show that the total rooftop area in Longhu District is 17.2 km2, with a rooftop PV available area of 12.7 km2. It is estimated that the rooftop PV installed capacity in Longhu District is 1849.4 MW, with an annual power generation of 2219.3 GWh.

Developing a 10-Layer Retinal Segmentation for MacTel Using Semi-Supervised Learning.

Automated segmentation software in optical coherence tomography (OCT) devices is usually developed for and primarily tested on common diseases. Therefore segmentation accuracy of automated software can be limited in eyes with rare pathologies. We sought to develop a semisupervised deep learning segmentation model that segments 10 retinal layers and four retinal features in eyes with Macular Telangiectasia Type II (MacTel) using a small labeled dataset by leveraging unlabeled images. We compared our model against popular supervised and semisupervised models, as well as conducted ablation studies on the model itself. Our model significantly outperformed all other models in terms of intersection over union on the 10 retinal layers and two retinal features in the test dataset. For the remaining two features, the pre-retinal space above the internal limiting membrane and the background below the retinal pigment epithelium, all of the models performed similarly. Furthermore, we showed that using more unlabeled images improved the performance of our semisupervised model. Our model improves segmentation performance over supervised models by leveraging unlabeled data. This approach has the potential to improve segmentation performance for other diseases, where labeled data is limited but unlabeled data abundant. Improving automated segmentation of MacTel pathology on OCT imaging by leveraging unlabeled data may enable more accurate assessment of disease progression, and this approach may be useful for improving feature identification and location on OCT in other rare diseases as well.

Physics-Informed Data-Driven Approaches to State of Health Prediction of Maritime Battery Systems

Battery systems are increasingly being used for powering ocean going ships, and the number of fully electric or hybrid ships relying on battery power for propulsion and maneuvering is growing. In order to ensure the safety of such electric ships, it is of paramount importance to monitor the available energy that can be stored in the batteries, and classification societies typically require that the state of health (SOH) of the batteries can be verified by independent tests – annual capacity tests. However, this paper discusses physics-informed data-driven approaches to online diagnostics for state of health monitoring of maritime battery systems based on a combination of physical knowledge, physic-based models, insights from extensive characterization tests and operational sensor data collected from the batteries during actual operation. This represents an alternative approach to the annual capacity tests for electric ships that is found to be sufficiently robust and accurate under certain conditions. Previous attempts with purely data-driven models, including both cumulative and snapshot models, semi-supervised learning and simple models based on the state of charge did not achieve the required reliability and accuracy for them to be utilized in a ship classification perspective, as presented at previous PHM conferences. However, preliminary results from the physics-informed data-driven method presented in this paper indicate that it can be relied on for independent verification of state of health as an alternative to physical tests. It has been tested on battery cells cycled in laboratory degradation tests as well as on field returns from batteries onboard ships in service. Notwithstanding, further validation and verification of the method is recommended to further build confidence in the model predictions.

Semi-supervised learning techniques for detection of dead pine trees with UAV imagery for pine wilt disease control

Semi-supervised learning techniques for detection of dead pine trees with UAV imagery for pine wilt disease control

NiReject: toward automated bad channel detection in functional near-infrared spectroscopy.

The increasing sample sizes and channel densities in functional near-infrared spectroscopy (fNIRS) necessitate precise and scalable identification of signals that do not permit reliable analysis to exclude them. Despite the relevance of detecting these "bad channels," little is known about the behavior of fNIRS detection methods, and the potential of unsupervised and semi-supervised machine learning remains unexplored. We developed three novel machine learning-based detectors, unsupervised, semi-supervised, and hybrid NiReject, and compared them with existing approaches. We conducted a systematic literature search and demonstrated the influence of bad channel detection. Based on 29,924 signals from two independently rated datasets and a simulated scenario space of diverse phenomena, we evaluated the NiReject models, six of the most established detection methods in fNIRS, and 11 prominent methods from other domains. Although the results indicated that a lack of proper detection can strongly bias findings, detection methods were reported in only 32% of the included studies. Semi-supervised models, specifically semi-supervised NiReject, outperformed both established thresholding-based and unsupervised detectors. Hybrid NiReject, utilizing a human feedback loop, addressed the practical challenges of semi-supervised methods while maintaining precise detection and low rating effort. This work contributes toward more automated and reliable fNIRS signal quality control by comprehensively evaluating existing and introducing novel machine learning-based techniques and outlining practical considerations for bad channel detection.

Pairpot: a database with real-time lasso-based analysis tailored for paired single-cell and spatial transcriptomics.

Paired single-cell and spatially resolved transcriptomics (SRT) data supplement each other, providing in-depth insights into biological processes and disease mechanisms. Previous SRT databases have limitations in curating sufficient single-cell and SRT pairs (SC-SP pairs) and providing real-time heuristic analysis, which hinder the effort to uncover potential biological insights. Here, we developed Pairpot (http://pairpot.bioxai.cn), a database tailored for paired single-cell and SRT data with real-time heuristic analysis. Pairpot curates 99 high-quality pairs including 1,425,656 spots from 299 datasets, and creates the association networks. It constructs the curated pairs by integrating multiple slices and establishing potential associations between single-cell and SRT data. On this basis, Pairpot adopts semi-supervised learning that enables real-time heuristic analysis for SC-SP pairs where Lasso-View refines the user-selected SRT domains within milliseconds, Pair-View infers cell proportions of spots based on user-selected cell types in real-time and Layer-View displays SRT slices using a 3D hierarchical layout. Experiments demonstrated Pairpot's efficiency in identifying heterogeneous domains and cell proportions.

An intelligent monitoring approach for urban natural gas pipeline leak using semi-supervised learning generative adversarial networks

Traditional gas pipeline leak monitoring methods are subjected to the long response times and high false alarm rates. Deep learning can enhance the accuracy and real-time performance of pipeline leak monitoring. This paper develops an intelligent monitoring approach for urban gas pipeline leaks based on a semi-supervised learning Generative Adversarial Network (SGAN). First, the Isolation Forest algorithm is used to classify anomalies in the collected process parameter data of urban natural gas pipelines. One-Hot Encoding is used to label a small amount of sample data of pipeline leak. Second, both the labeled and unlabeled data are input into SGAN model for semi-supervised learning and classification to monitor the state of urban gas pipeline leak. The methodology addresses the imbalance between pipeline leak status data and normal data. The comparison with GAN and MLP shows that the methodology reaches the highest values in all evaluation metrics (precision = 94.1%, accuracy = 95.63%, recall = 93.93%, F1 score = 94.32%). The superior performance and accuracy make it more effective for urban natural gas pipeline leak monitoring.

A growth posture identification method of immature peaches in natural environments

The precise bagging of immature peaches by the fruit bagging robot requires the identification of the target young fruits as well as the acquisition of their growth angles. The network models employed in single detection algorithms exhibit complexity and pose challenges for deployment on mobile terminals as they heavily rely on the availability of labeled samples. A semi-supervised learning and lightweight strategy based on YOLOv8n-seg was proposed to identify the growth posture of immature peaches in the work. Firstly, the self-training method and data enhancement in semi-supervised learning were used to generate efficient pseudo-label data. A tremendous labeling workload was solved. Secondly, the YOLOv8n-seg backbone network was replaced with an improved MobileNetv3 structure for better real-time detection on MT to reduce network parameters and calculations. The model was easily deployed with improved detection speed. Meanwhile, the original upsampling module was replaced with the CARAFE module to enhance the recognition capability of global features, which considered the impact of immature peaches on the nearby color background. The CIOU loss function was ultimately substituted with the SIOU loss function to further optimize the boundary frame loss and target detection accuracy. The enhanced model could predict the coordinate information of immature peaches and calculate growth angles. The experimental results show that the improved peach seedling growth posture network model has a weight size of only 23.1% of the original model. Additionally, the algorithm achieved a remarkable rate of 87.8% in identifying young peach fruits, with an average error of ±3.3° in estimating the growth angle. It took an average of 31 ms to detect a 3024 × 4032 pixels image in the edge computing device JETSON AGX ORIN CLB development kits. The method could rapidly identify immature peaches and estimate the growth angle, which ensured accurate bagging.

DyConfidMatch: Dynamic thresholding and re-sampling for 3D semi-supervised learning

Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance, especially in 3D contexts. This study investigates class-level confidence as an indicator of learning status in 3D SSL, proposing a novel method that utilizes dynamic thresholding to better use unlabeled data, particularly from underrepresented classes. A re-sampling strategy is also introduced to mitigate bias towards well-represented classes, ensuring equitable class representation. Through extensive experiments in 3D SSL, our method surpasses state-of-the-art counterparts in classification and detection tasks, highlighting its effectiveness in tackling data imbalance. This approach presents a significant advancement in SSL for 3D datasets, providing a robust solution for data imbalance issues.

Using Semi-supervised Machine Learning to Assist Classification and Recognition of Chinese Vernacular Architecture

In order to construct a more refined, comprehensive and systematized classification system for Chinese vernacular architecture, this paper proposed a classifying method based on semi-supervised machine learning using architecture image data. By adding type labels based on experts' prior knowledge as a guide to part of the training samples, it allows generalized machine clustering to effectively combine image feature mining with characteristics of special objects. Taking the scheme of machine clustering as a reference, a classification system for Chinese vernacular architecture with 9 major categories and 23 subcategories was established, which boasts extensive coverage of vernacular architectural types and has strong distinguishability. This method integrates the advantages of expert knowledge and computer algorithm, and can be utilized as a reference for studies where unsupervised or fully supervised machine learning is challenging to apply. In addition, the YOLOv8 object detection algorithm of deep learning is also applied to construct a corresponding recognition model for these architectural categories, which performs well in terms of recognition accuracy and robustness. This tool holds significant potential for application in heritage protection and urban and rural planning.

A Novel Landmark-based Semi-supervised Deep Learning Method for Cerebral Aneurysm Detection Using TOF-MRA

Background: Time-of-flight (TOF) magnetic resonance angiography (MRA) is widely used to identify aneurysm in human brain. Various deep learning models have been developed to help TOF-MRA reading in the field. The performance of those TOF-MRA analysis tools, however, faces several limitations in cerebral aneurysm detection. These challenges primarily come from the fact that cerebral aneurysms occupy less than 0.1% of the total TOF-MRA voxel size. This study aims to improve the efficiency of cerebral aneurysm detection by developing a landmark-based semi-supervised deep learning method, a technology that automatically generates landmark boxes in areas with a high probability of cerebral aneurysm occurrence.Methods: We used data from a total of 500 aneurysm-positive and 50 aneurysm-negative subjects. The aneurysm detection model was developed using clustering and a dilated residual network.Results: When the number of landmarks was ten and their size was 36 mm<sup>3</sup>, the best performance was achieved in our experiment. Although landmark occupies a small portion of the entire image, up to 98.2% of landmarks were cerebral aneurysms. The sensitivity of the model for cerebral aneurysm detection was 83.0%, with a false positive rate of 3.4%.Conclusions: This study developed a deep learning model using TOF-MRA image. This model generates the most suitable landmarks for each individual, excluding unnecessary areas for cerebral aneurysm detection, which makes it possible to focus on areas with a high probability of occurrence. This model is expected to enhance the efficiency and accuracy of cerebral aneurysm detection in the field.

Applications of cluster-based transfer learning in image and localization tasks

Transfer learning can address the issue of insufficient labels in machine learning. Using knowledge in a labeled domain (source domain) can assist in acquiring and learning knowledge in a domain (target domain) that lacks some or all labels. In this paper, we propose a new cluster-based semi-supervised transfer learning (CBSSTL) under a new assumption that samples in the target domain are unlabeled but contain cluster information. Furthermore, we propose a new transfer learning framework and a method for fine-tuning parameters. We tested and compared the proposed method with other unsupervised and semi-supervised transfer learning methods on well-known image datasets. The experimental results demonstrate the effectiveness of the proposed method. Additionally, we created a localization dataset for transfer learning. Finally, we tested and analyzed the proposed method on this dataset. Its particularly challenging nature makes it difficult for our method to work effectively.