Neural Networks最新文献

{"title":"ReTri: Progressive domain bridging via representation disentanglement and triple-level consistency-driven feature alignment for unsupervised domain adaptive medical image segmentation","authors":"Xiaoru Gao ,&nbsp;Guoyan Zheng","doi":"10.1016/j.neunet.2026.108564","DOIUrl":"10.1016/j.neunet.2026.108564","url":null,"abstract":"<div><div>Unsupervised domain adaptation (UDA) in medical image segmentation presents significant challenges due to substantial cross-domain disparities and the inherent absence of target domain annotations. In this study, to address these challenges, we propose an end-to-end progressive domain bridging framework based on representation disentanglement and triple-level consistency-driven feature alignment, referred to as ReTri, that synergistically integrates a representation disentanglement-based image alignment (RDIA) module with a novel triple-level consistency-driven feature alignment (TCFA) module. In particular, the RDIA module aims to establish an initial domain bridge by decoupling and aligning fundamental visual disparities through disentangled representation learning, while the novel TCFA module hierarchically bridges remaining cross-domain semantic discrepancies and feature distribution disparities via two novel consistency-driven alignment mechanisms: 1) attention-guided semantics-level consistency alignment, where we purposely design a bi-attentive semantic feature extraction (BSFE) component coupled with an attention-adaptive semantic consistency (ASC) loss function, facilitating dynamic alignment of high-level semantic representations across domains, and 2) multi-view dual-level mixing consistency alignment, consisting of Feature-Cut consistent self-ensembling (FCCS) and Trans-Cut consistent self-ensembling (TCCS) components. These two components operate within intermediate mixing spaces to ensure robust knowledge transfer through complementary feature- and prediction-level consistency regularization. Extensive experimental evaluations are conducted on four challenging datasets (Lumbar Spine CT-MR, Cardiac CT-MR, Cross-domain Echocardiography, and Multi-center Prostate MR) across seven UDA-based segmentation scenarios and two external validation scenarios. Our framework achieves superior performance over the best state-of-the-art (SOTA) methods on following UDA-based segmentation scenarios: +2.9% DSC for spine CT → MR segmentation, +3.6% and +2.4% DSC for bidirectional cardiac CT↔MR segmentation, +1.7% and +2.3% DSC for bidirectional cross-center cross-vendor Echocardiography (CAMUS↔EchoNet-Dynamic) segmentation, and +12.2% and +12.0% DSC for bidirectional multi-center prostate MR segmentation. The source code and the datasets are publicly available at <span><span>https://github.com/xiaorugao999/ReTri</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108564"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145981537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An online forecasting-based fine-tuning pipeline for time-series anomaly prediction","authors":"Zhou Zhou ,&nbsp;Van Hoan Trinh ,&nbsp;Yuet Ming Joyce Yue ,&nbsp;Dit-Yan Yeung ,&nbsp;Ka-Hing Wong ,&nbsp;Wai-Kin Wong","doi":"10.1016/j.neunet.2026.108568","DOIUrl":"10.1016/j.neunet.2026.108568","url":null,"abstract":"<div><div>Time-series anomaly detection is critical for numerous real-world applications and has been extensively studied. However, existing methods are typically designed to identify anomalies within a complete time series. In other words, they rely on access to ground truth data to calculate anomaly scores and distinguish anomalous data from normal patterns. This reliance limits their applicability in scenarios where predicting future anomalies is required, as the ground truth is inherently unavailable. To address this gap, we introduce the concept of <em>Time-Series Anomaly Prediction</em> (<em>TSAP</em>), which focuses on forecasting the occurrence and progression of anomalies in time series simultaneously without relying on ground truth. In this paper, we propose a novel exemplar-based pre-training and fine-tuning pipeline tailored to this task, based on recent achievements in online time-series forecasting techniques. The pipeline begins with an offline pre-training phase, where a deep learning model is trained to capture the underlying temporal correlations in time-series data. During the online fine-tuning stage, a three-step process is employed to predict the timing and evolution of anomalies. This process includes prediction and anomaly detection, motif search for similar patterns, and fine-tuning using exemplars. These steps are repeated as new data arrives. We evaluate the proposed method against state-of-the-art approaches from various relevant categories on both real-world and synthetic datasets. Experimental results show that the proposed method improves anomaly detection accuracy by up to 53.8% in terms of F1 score and enhances time-series forecasting accuracy during and after anomaly periods by up to 82.4% and 49.1% in terms of MSE. Through analysing the results, we prove the proposed method’s effectiveness in addressing the new <em>TSAP</em> tasks, which are incapable of being handled by current time-series anomaly detection or online time-series forecasting methods.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108568"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145981635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implicit neural network-based coal SEM super-resolution for enhancing micro-pores measurement tasks","authors":"Xiaowei An ,&nbsp;Shenghua Teng ,&nbsp;Zhuopeng Wang ,&nbsp;Quanquan Liang","doi":"10.1016/j.neunet.2026.108578","DOIUrl":"10.1016/j.neunet.2026.108578","url":null,"abstract":"<div><div>Prolonged radiation exposure in coal Scanning Electron Microscopy (SEM) poses structural damage risks to specimens during high-resolution observation. To mitigate this situation, we propose an interactive-interpretable super-resolution (SR) framework that integrates implicit neural representation (INR) with model-driven Half-Quadratic Splitting (HQS) optimization. Specifically, the implicit neural representation employs a local window attention mechanism to capture contextual dependencies across reconstructed regions. Furthermore, an interactive dual-branch network decouples feature content and positional encoding, providing an initial solution for the subsequent HQS optimization. By unfolding the HQS algorithm into a deep network, each layer corresponds to an explicit and interpretable optimization step with the explicit mathmatical transparency. Experimental results demonstrate that our method outperforms the related state-of-the-art SR algorithms in visual fidelity and exhibits the applicability and stability in downstream geometry-sensitive measurement tasks.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108578"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145981538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Taming polarized fitting: BLINEX-Pcomp with asymmetric risk penalty for robust Pcomp classification","authors":"Long Tang ,&nbsp;Xin Si ,&nbsp;Yingjie Tian ,&nbsp;Panos M Pardalos","doi":"10.1016/j.neunet.2026.108580","DOIUrl":"10.1016/j.neunet.2026.108580","url":null,"abstract":"<div><div>As a novel paradigm for learning with inexact supervision, Pcomp classification reduces the annotation costs of training a binary classifier by using ordered pairwise samples without requiring precise labels. However, existing methods fail to fully account for sign differences in empirical risk at the level of individual sample pairs, resulting in polarized fitting where the risks of overfitting and underfitting coexist. Actually, positive and negative empirical risks indicate varying degrees of training difficulty, necessitating differentiated treatments. In this work, we propose a BLINEX-Pcomp model that employs a bounded linear-exponential function to impose distinct penalties on positive and negative risks for each sample pair. The BLINEX-Pcomp model dynamically shifts the training focus toward challenging sample pairs, well balancing pairwise-level risks of overfitting and underfitting. Additionally, a multi-view version of BLINEX-Pcomp (MV-BLINEX-Pcomp) is developed to further enhance performance by integrating multi-view features. We have theoretically verified that MV-BLINEX-Pcomp degrades to BLINEX-Pcomp when only a single view of features is available. A dual-stage solver is designed to train the MV-BLINEX-Pcomp model. Exciting numerical results from comparative experiments validate the effectiveness of our methods in tackling Pcomp classification.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108580"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145981714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PMNO: A novel physics guided multi-step neural operator predictor for partial differential equations","authors":"Jin Song ,&nbsp;Kenji Kawaguchi ,&nbsp;Zhenya Yan","doi":"10.1016/j.neunet.2026.108593","DOIUrl":"10.1016/j.neunet.2026.108593","url":null,"abstract":"<div><div>Neural operators, which aim to approximate mappings between infinite-dimensional function spaces, have been widely applied in the simulation and prediction of physical systems. However, the limited representational capacity of network architectures, combined with their heavy reliance on large-scale data, often hinder effective training and result in poor extrapolation performance. In this paper, inspired by traditional numerical methods, we propose a novel Physics guided Multi-step Neural Operator (PMNO) architecture to address these challenges in long-horizon prediction of complex physical systems. Distinct from general operator learning methods, the PMNO framework replaces the single-step input with multi-step historical data in the forward pass and introduces an implicit time-stepping scheme based on the Backward Differentiation Formula (BDF) during backpropagation. This design not only strengthens the model’s extrapolation capacity but also facilitates more efficient and stable training with fewer data samples, especially for long-term predictions. Meanwhile, a causal training strategy is employed to circumvent the need for multi-stage training and to ensure efficient end-to-end optimization. The neural operator architecture possesses resolution-invariant properties, enabling the trained model to perform fast extrapolation on arbitrary spatial resolutions. We demonstrate the superior predictive performance of PMNO predictor across a diverse range of physical systems, including 2D linear system, modeling over irregular domain, complex-valued wave dynamics, and reaction-diffusion processes. Depending on the specific problem setting, various neural operator architectures, including FNO, DeepONet, and their variants, can be seamlessly integrated into the PMNO framework.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108593"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Source Temporal-Depth fusion for robust end-to-End visual odometry","authors":"Sihang Zhang ,&nbsp;Congqi Cao ,&nbsp;Qiang Gao ,&nbsp;Ganchao Liu","doi":"10.1016/j.neunet.2026.108598","DOIUrl":"10.1016/j.neunet.2026.108598","url":null,"abstract":"<div><div>End-to-end visual odometry models have recently achieved localization accuracy on par with conventional techniques, while effectively reducing the occurrence of catastrophic failures. However, the relevant models cannot leverage the complete time-series data for pose adjustment and optimization. Moreover, these models are limited to using joint depth prediction tasks merely as a means of scale constraint, lacking effective utilization of depth information. In this paper, we propose an end-to-end multi-source visual odometry (MVO) model that dynamically integrates the key components of hybrid visual odometry pipelines into a unified, learnable deep framework. Specifically, we propose TimePoseNet to model the mapping relationship from time to pose, capturing temporal dependencies across the entire sequence. Additionally, a wavelet convolutional attention mechanism is employed to extract global depth information from the depth map, which is then directly embedded into the pose features to dynamically constrain scale ambiguity. Furthermore, temporal and depth cues are jointly incorporated into the post-processing stage of pose estimation. The proposed method attains state-of-the-art performance on both the KITTI benchmark and the newly introduced UAV-2025 dataset, while preserving computational efficiency during inference.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108598"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CBAM-ST-GCN: An enhanced DRL-based end-to-end visual navigation framework for mobile robot","authors":"Mingyang Xie,&nbsp;Wei Yu,&nbsp;Huanyu Jin,&nbsp;Wei Li,&nbsp;Xin Chen","doi":"10.1016/j.neunet.2026.108622","DOIUrl":"10.1016/j.neunet.2026.108622","url":null,"abstract":"<div><div>Visual-based navigation for mobile robot poses significant challenges due to limited visual perception and the presence of unforeseen dynamic obstacles. Deep reinforcement learning (DRL) provides an end-to-end solution by directly mapping raw sensor data to control commands, offering high adaptability and reduced reliance on handcrafted rules. However, high-dimensional visual inputs and the non-stationarity introduced by dynamic obstacles easily make the policy learning of DRL difficult to convergent and unstable. In this paper, an enhanced end-to-end visual navigation framework is proposed for mobile robot operating in dynamic environments, denoted as CBAM-ST-GCN. A convolutional block attention module (CBAM) is introduced into the framework to enhance visual perception by assigning attention weights across spatial and temporal dimensions. Furthermore, a spatio-temporal graph convolutional network (ST-GCN) is designed to capture the behavior features of moving obstacles. In addition, a velocity obstacle (VO) method-based penalty term is incorporated into the reward function for the enhancement of collision avoidance. Extensive simulation results demonstrate that the proposed method achieves superior success rates and significantly higher convergence speed. Real-world experiments further validate the effectiveness and adaptability of the proposed approach in practical scenarios.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108622"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MambaFPN: A SSM-based feature pyramid network for object detection","authors":"Le Liang ,&nbsp;Cheng Wang ,&nbsp;Lefei Zhang","doi":"10.1016/j.neunet.2026.108544","DOIUrl":"10.1016/j.neunet.2026.108544","url":null,"abstract":"<div><div>Object detection is a fundamental task in computer vision, aiming to localize and classify objects within images. Feature pyramid networks (FPNs) play a crucial role in modern object detectors by constructing hierarchical multi-scale feature maps to effectively handle objects of varying sizes. However, most existing advanced FPN methods rely heavily on convolutional neural networks (CNNs), which struggle to capture global context information. To address this limitation, we propose leveraging vision mamba blocks to enhance global modeling capabilities. The vanilla vision mamba block, through its state space mechanism, enables global context modeling for every spatial pixel within a single feature map. Building on this, we first use vision mamba blocks to extract global information from individual feature maps in the hierarchy. Subsequently, additional vision mamba blocks facilitate inter-scale information exchange among multi-scale feature maps, ensuring comprehensive global context integration. The proposed method, termed MambaFPN, significantly enhances object detector performance. For instance, it improves the Average Precision (AP) of vanilla FPN from 38.6 to 39.4, with fewer parameters. This demonstrates the effectiveness and efficiency of MambaFPN in advancing object detection.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108544"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hippocampus-centered structural covariance network reorganization in Alzheimer’s disease: An individualized graph-based biomarker validated by machine learning","authors":"Weiye Lu ,&nbsp;Qian Gong ,&nbsp;Yuna Chen ,&nbsp;Shijun Qiu ,&nbsp;Jie An","doi":"10.1016/j.neunet.2026.108542","DOIUrl":"10.1016/j.neunet.2026.108542","url":null,"abstract":"<div><div>Alzheimer’s disease (AD) is characterized by progressive brain network disintegration, yet quantifying this process at an individual level remains challenging. This study explores the potential of an individualized differential structural covariance network (IDSCN) as a graph theory-based biomarker to capture disease-specific network reorganization. We found that throughout the AD spectrum, significant progressive atrophy occurred in multiple brain regions, especially the hippocampus. At the same time, the brain underwent a profound structural covariant reorganization, and this reorganization was significantly centered on the hippocampus. Graph theory analysis revealed a significant enhancement in nodal strength and nodal efficiency across widespread brain regions, with the hippocampus, amygdala, middle temporal gyrus, and entorhinal cortex emerging as core hubs of pathological impact. Importantly, betweenness centrality selectively increased only in the bilateral hippocampus, highlighting their critical role as bridges in the pathological propagation network. Machine learning validation confirmed that this individualized network biomarker performs excellently in distinguishing AD patients from cognitively normal individuals, demonstrates comparable efficacy to traditional morphological models in capturing early disease-related changes, and shows potential in differentiating between mild cognitive impairment converters and non-converters. Our study establishes the hippocampus-centered IDSCN as an effective, individualized graph theory-based biomarker, providing new insights into the network pathophysiology of AD and holding significant potential for early diagnosis and prognostic stratification.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108542"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145941312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SAGCN: A syntactic aware multi-branch graph attention network with structural bias for aspect sentiment triplet extraction","authors":"Xin Xiao ,&nbsp;Bin Gao ,&nbsp;Zelong Su ,&nbsp;Linlin Li ,&nbsp;Shutian Liu ,&nbsp;Zhengjun Liu","doi":"10.1016/j.neunet.2026.108596","DOIUrl":"10.1016/j.neunet.2026.108596","url":null,"abstract":"<div><div>Aspect-based sentiment triplet extraction (ASTE), a newly developed and complex subtask within aspect-based sentiment analysis, focuses on detecting aspect terms, opinion terms, and establishing sentiment polarity from human language, thereby extracting triplets composed of these three elements. Although numerous methods have been developed in previous research to tackle this task, these ASTE methods exhibit weak interactions in constructing contextual representations and overlook the syntactic relationships between aspect terms and opinion terms. Therefore, this paper proposes a syntax-aware multi-branch graph attention network to address this issue. We have designed an efficient approach that integrates new structural biases into pre-trained language models through adapters to enhance the original mappings in self-attention, significantly reducing the parameter requirements and achieving lower latency. Simultaneously, we have devised a syntax-aware attention mechanism that not only discerns edges with varying dependency types as well as those with identical types, learning the representation of each edge in the graph relying on the dependency types of neighboring edges, thereby enabling more accurate graph propagation. Finally, we have designed a special fusion interaction layer that achieves the final text representation by merging different branch features with varying weights. Through a range of tests performed on four widely accessible datasets, it was demonstrated that the introduction of structural bias adapters is both effective and efficient. The proposed method improved the average F1 score by up to 4.11% compared to all baseline models, while also exhibiting good interpretability. Additionally, the experimental results highlighted the robustness and effectiveness of SAGCN, significantly outperforming the compared state-of-the-art baseline models.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"198 ","pages":"Article 108596"},"PeriodicalIF":6.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146031529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}