The analysis of carotid arteries, particularly plaques, in multi-sequence Magnetic Resonance Imaging (MRI) data is crucial for assessing the risk of atherosclerosis and ischemic stroke. In order to evaluate metrics and radiomic features, quantifying the state of atherosclerosis, accurate segmentation is important. However, the complex morphology of plaques and the scarcity of labeled data poses significant challenges. In this work, we address these problems and propose a semi-supervised deep learning-based approach designed to effectively integrate multi-sequence MRI data for the segmentation of carotid artery vessel wall and plaque. The proposed algorithm consists of two networks: a coarse localization model identifies the region of interest guided by some prior knowledge on the position and number of carotid arteries, followed by a fine segmentation model for precise delineation of vessel walls and plaques. To effectively integrate complementary information across different MRI sequences, we investigate different fusion strategies and introduce a multi-level multi-sequence version of U-Net architecture. To address the challenges of limited labeled data and the complexity of carotid artery MRI, we propose a semi-supervised approach that enforces consistency under various input transformations. Our approach is evaluated on 52 patients with arteriosclerosis, each with five MRI sequences. Comprehensive experiments demonstrate the effectiveness of our approach and emphasize the role of fusion point selection in U-Net-based architectures. To validate the accuracy of our results, we also include an expert-based assessment of model performance. Our findings highlight the potential of fusion strategies and semi-supervised learning for improving carotid artery segmentation in data-limited MRI applications. • Segmentation of carotid arteries and pathological changes in multi-sequence MRI data. • Utilization of semi-supervised learning for multi-sequence segmentation. • Introduction of a novel prior on the symmetry and number of carotid arteries. • Analysis of different fusion points for multi-sequence data. • Independent segmentation of carotid arteries’ vessel wall and plaques.

• TM forms interpretable patterns-clauses that collectively recognize and classify data • Class patterns are constructed through conjunctions of common Boolean features • TM’s hyper-parameters balance clauses specialization, generalization and coverage • TM clustering potential opens avenues for unsupervised and semi-supervised learning • Clause-level convergence offers a practical metric for TM training completion The inability to trace an AI’s reasoning process and understand why it makes each decision is known as the black box problem. This remains one of the major barriers to the trusted and widespread use of machine learning in many application domains. The paper explores pattern recognition performance and learning dynamics of the Tsetlin Machine – a new explainable logic-based machine-learning approach. Tsetlin Machine uses a collection of finite-state automata with a unique logic-based learning mechanism and provides a promising alternative to Artificial Neural Networks with several advantages, such as interpretability, low complexity, suitability for hardware implementation and high performance. This work investigates Tsetlin Machine’s mechanism for constructing conjunctive clauses from data and their interpretation for pattern recognition on several datasets. We demonstrate that during training the logical clauses learn persistent sub-patterns within the class. Each clause creates a class template by clustering a certain number of similar class samples, combining them through literal-wise logical conjunction (i.e., AND-ing). The number of class samples that each clause combines depends on Tsetlin Machine’s hyperparameters. The more class samples that are combined, the more general the clauses become. The paper aims at uncovering how Tsetlin Machine’s hyperparameters influence the balance between clause generalization and specialization and how this affects the accuracy of pattern recognition. It also studies the evolution of the machine’s internal state, its convergence and training completion.

Beyond Human Variability: Deep Learning for Intravascular Ultrasound Segmentation With Noisy Labels.

Integrating semi-supervised and active learning for semantic segmentation

Semi-supervised dual-teacher comparative learning with bidirectional balanced copy-paste for medical image segmentation

Wire-laser directed energy deposition (WL-DED) enables the fabrication of large-scale metallic components but frequently suffers from process-induced surface defects that hinder part quality and increase post-processing costs. Automated inspection is challenging because defects are diverse and rare, making large labelled datasets impractical. This paper proposes an interpretable semi-supervised framework for surface detection and localization on WL-DED components using high-density 3D point clouds acquired by laser scanning. The workflow includes point-cloud preprocessing, patch-based segmentation, voxelization, and semi-supervised representation learning of defect-free surface morphology. Two 3D deep autoencoder models, i.e., a convolutional autoencoder (CAE) and a variational autoencoder (VAE), are trained exclusively on normal patches and detect anomalies through voxel-wise reconstruction errors. Defects are localized by mapping reconstruction-error heatmaps back onto the original surface, enabling quantitative visualization of defect severity. Experimental results on WL-DED thin-wall samples show that the optimized CAE achieves 86.09% precision, while the VAE reaches 86.43% precision with improved defect localization (mIoU up to 0.7234). Activation-map analysis provides interpretability by highlighting geometric regions that drive anomaly responses. A hyperparameter study demonstrates that lower voxel resolutions and smaller patch sizes improve robustness and reduce false positives. The proposed framework generalizes to more complex multi-bead, multi-layer structures with minimal retraining, supporting practical deployment for intelligent inspection and decision-making in additive manufacturing quality assurance.

GNS2CCL: A graph network semi-supervised concept-cognitive learning model for node classification

1S-MambaMatch: A semi-supervised and One-shot learning framework with Multi-input Visual State Space Model for skin lesion segmentation

Semi-supervised learning driven algorithm for reconstructing environment temperature field using acoustic tomography

Inferring energy consumption of offshore wind turbine components: using deep semi-supervised learning with radial basis function kernel

Accurate flower-load assessment is critical for informed thinning strategies in orchard management. UAV-based deep learning automated counting offers efficiency advantages, yet precise counting is heavily dependent on abundant annotated data, which is scarce and costly to obtain in agricultural settings. While semi-supervised learning alleviates dependency on manual annotation, its application to UAV-based orchard imagery faces challenges: complex backgrounds and small target sizes, which undermine pseudo-label reliability. To address these challenges, this study proposes a two-stage framework to achieve separate counting of apple flowers at different phenological stages. First, a color-SAM flower extractor (CSAM-FE) is proposed to preprocess images using a strategy combining color thresholding with the Segment Anything Model (SAM), suppressing background noise and extracting high-quality flower clusters, thereby providing purified inputs for the subsequent counting network. Second, an uncertainty-guided semi-supervised flower counting network (USCount-Net) is proposed for accurate stage-specific flower counting with limited labeled data. The USCount-Net incorporates two key components: an adaptive pseudo-label filtering (PLF) mechanism based on frequent forward uncertainty estimation (FFUE) is designed to dynamically suppress noisy gradient backpropagation, mitigating error propagation from unreliable pseudo-labels; and a noise-sensitive adaptive gated fusion (AGF) module is introduced to fuse cross-scale features without redundancy, addressing significant scale variations across phenological stages and observation angles. Comparative experiments on a self-built apple flower counting dataset demonstrate that USCount-Net achieves lower MAE and RMSE than state-of-the-art methods at 10%, 30%, and 50% labeling ratios. The results demonstrate that the proposed methodology serves as methodological support for rapid and precise apple flower counting in low-annotation agricultural scenarios.

SNMatch: A unified diversely sample selection framework for long-tailed semi-supervised learning

Early detection of gearbox faults in wind turbines using a fine-tuned transformer encoder

Attempts to deploy computer vision in agricultural tasks often suffer from a shortage of annotated data. One strategy to alleviate the impact of limited data is Self-Supervised Learning (SSL), which involves pre-training a model on a pretext task that utilizes automatically generated annotations. The primary objective of this study is to leverage a multi-camera view dataset of cotton boll images for contrastive learning in order to enable phenotyping tasks with minimal data annotation. This dataset was collected in the field using six camera views. The efficacy of two contrastive learning frameworks (SimCLR and MoCo) in producing representations when positive examples originate from different cameras was investigated, and a comprehensive study of how the camera positions affect performance was conducted. After self-supervised pre-training, linear evaluation and semi-supervised learning experiments were performed on boll detection and plot status downstream tasks. In general, using multiple camera views with SimCLR and MoCo improves cotton boll detection mean average precision by 14% compared to vanilla SimCLR and MoCo. Through careful investigation using synthetic data, it was determined that relative camera poses with an intermediate amount of overlap seem more likely to perform well. Neither MoCo nor SimCLR was consistently superior to the other in this context. The representations embed meaningful features about the cotton plants, such as overall boll density, but also less meaningful ones, such as lighting variations. This technique could potentially accelerate the development of phenotyping algorithms based on data collected from field robots. • A contrastive learning method based on comparing multi-camera views was developed. • The method was tested with images of cotton bolls from a ground robot. • The method outperformed baseline contrastive learning approaches.

Decoding urban soundscapes: spatial prediction and influence mechanism analysis with interpretable semi-supervised learning

In the era of digital transformation, datacenters and High Performance Computing (HPC) Systems have emerged as the backbone of global technology infrastructure, powering essential services across various industries, including finance and healthcare. Therefore, ensuring the uninterrupted service of these datacenters has become a critical challenge. Thermal anomalies pose a significant risk to datacenter operation, potentially leading to hardware deterioration, system downtime, and catastrophic failures. This threat is exacerbated by the growing number of datacenters, increased power density, and heat waves fostered by global warming. Detecting thermal anomalies in datacenters involves several challenges. Large-scale data collection is difficult, requiring diverse monitoring signals from thousands of nodes over long periods. The absence of labeled data complicates the identification of normal and abnormal states. Establishing accurate classification thresholds to minimize false positives and negatives is another significant hurdle. Traditional statistical methods often fail to capture temporal dependencies and complex correlations in monitoring signals. Additionally, finding anomalies at both the system and subsystem levels adds to the complexity. Deploying machine learning models in production environments presents technical and operational challenges, making real-time anomaly detection a demanding task. This paper introduces ThermADNet, a Thermal Anomaly Detection framework that combines statistical rules-based methods with Deep Neural Network (DNN) techniques for thermal anomaly detection in datacenters. ThermADNet utilizes a semi-supervised learning approach by training on a ”semi-normal” dataset, addressing the challenges of large-scale data collection, semi-normal dataset identification, and classification threshold establishment. This framework’s efficacy is validated by its success in identifying real physical thermal failure events within a Tier-0 datacenter, pinpointing anomalies at both the system and subsystem levels, including compute nodes and datacenter infrastructure. In the critical evaluation window covering the July 28 failure, ThermADNet achieves precision and recall up to 0.97, with F1-scores as high as 0.97. By providing detailed information about anomalies, the framework clarifies the characteristics and reasoning behind the DNN outputs, thereby building trust in the AI model and ensuring that users can understand and rely on the system’s decisions. By offering a sophisticated method for thermal anomaly detection, ThermADNet significantly contributes to enhancing datacenter reliability and efficiency. This advancement supports the uninterrupted operation of critical HPC systems, averting considerable economic and societal losses.

Noninvasive intracranial hypertension detection using machine-learning of cerebral blood flow velocity waveforms

Progressive semi-supervised learning for multimodal pneumonia diagnosis

Domain adaptation (DA) seeks to utilize ample labeled data from a source domain to boost the generalization capability of models on an unlabeled target domain with divergent data distributions. Label Propagation (LP) has emerged as an efficient semi-supervised learning paradigm for DA, transferring labels between the source and target domains based on a similarity graph. Nevertheless, existing LP-based DA methods still face significant challenges: (1) Semantic insufficiency in the source training domain impairs the performance of classes with sparse structures, particularly minority classes; (2) Generated pseudo-labels exhibit low reliability due to ambiguous feature distributions; (3) The two-phase architecture decouples domain-invariant feature learning from label propagation, thus failing to achieve mutual enhancement between these two processes for DA tasks; (4) Sample-level graph construction incurs prohibitive computational costs and poor scalability when handling large-scale datasets. To address these issues, we propose a novel DA strategy, Deep Transferable Label Propagation (DTLP), that integrates prototypical augmentation techniques. Specifically, DTLP embeds three core modules into a unified end-to-end system: (1) Prototype-guided feature augmentation, termed Prototypical Augmentation (ProAug), which enriches the semantic content of the source domain by interpolating samples with class prototypes to mitigate semantic deficiency; (2) Prototype graph-based label propagation, which constructs a class-level prototypical graph rather than a sample-level one to reduce computational complexity and alleviate class imbalance; (3) Domain alignment via prototypical contrastive learning, which facilitates dynamic mutual optimization between domain-invariant feature extraction and robust label propagation while narrowing domain discrepancy. Comprehensive experiments on various benchmark datasets demonstrate that the proposed DTLP outperforms state-of-the-art LP-based DA methods, validating its effectiveness and generalizability.

While long-tailed semi-supervised learning (LTSSL) has attracted growing attention in many real-world classification tasks, existing LTSSL algorithms typically assume that labeled and unlabeled data share nearly identical class distributions. When this assumption is violated, these methods can perform poorly because they rely on biased model-generated pseudo-labels. To address this issue, we propose a simple yet effective approach called DeCon for LTSSL with unknown unlabeled class distributions. Specifically, DeCon decouples learning into two specialized branches: a standard branch that focuses on head classes and a balanced branch that focuses on tail classes. During training, the two branches interact and gradually converge, allowing them to complement each other and ultimately achieve strong performance across all classes. Despite its simplicity, we show that DeCon achieves state-of-the-art performance on a variety of standard LTSSL benchmarks, e.g., an averaged 2.7% absolute increase in test accuracy against existing algorithms when the class distributions of labeled and unlabeled data are mismatched. Even when the class distributions are identical, DeCon consistently outperforms many sophisticated LTSSL algorithms. Furthermore, we conduct extensive ablation analyses to tease apart the factors that are the most important to the success of DeCon. The source code is available at https://github.com/Gank0078/DeCon.