Neural Networks最新文献

{"title":"Scalable memory synthesis for exemplar-free lifelong person re-identification.","authors":"Hancai Liu, Jican Tan, Haifeng Yang, Jinjia Peng, Huibing Wang","doi":"10.1016/j.neunet.2026.109649","DOIUrl":"https://doi.org/10.1016/j.neunet.2026.109649","url":null,"abstract":"<p><p>Lifelong person re-identification (LReID) aims to learn from streaming data sources step by step, which suffers from catastrophic forgetting. In the exemplar-free LReID setting, some existing works generate pseudo-images to approximate past-domain data distributions in order to alleviate forgetting. However, such pixel-level replay strategies mainly align low-level appearance statistics such as color and style, and often neglect explicit constraints on the geometric structure of old identities in the embedding space, which tends to lead to continuous performance degradation and aggravated forgetting on past domains. To address this issue, this paper proposes Scalable Memory Synthesis (SMSyn), which constructs a controllable synthetic memory to maintain instance-level separability during continual updates. The Prototype Variational Synthesizer (PVS) generates pseudo-samples around historical instances to enrich and reconstruct historical knowledge. Then, the Feature Space Preservation (FSP) module constrains samples to concentrate around their corresponding class centers while maintaining inter-class relationships and local neighborhood structures, thereby counteracting geometric inflation and suppressing the accumulation of identity-geometry degradation. Experiments demonstrate that SMSyn outperforms state-of-the-art LReID methods.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"205 Pt C","pages":"109649"},"PeriodicalIF":7.2,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149031808","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":"MNet: A Mamba-based teacher-student-decoder framework for multimodal remote sensing segmentation.","authors":"Mengmeng Liu, Ronghua Shang, Jingyu Zhong, Kang Liu, Yangyang Li, Jie Feng","doi":"10.1016/j.neunet.2026.109645","DOIUrl":"https://doi.org/10.1016/j.neunet.2026.109645","url":null,"abstract":"<p><p>Remote sensing image segmentation serves as a fundamental step in connecting raw data with high-level vision understanding. However, single-modality inputs, such as optical or SAR imagery, often provide incomplete semantics, thereby limiting segmentation accuracy. While recent state space models (e.g., Mamba) have shown strong performance in unimodal segmentation by modeling long-range dependencies efficiently, their potential in multimodal settings remains largely unexplored. To address this gap, we propose MNet, a Mamba-based Teacher-Student-Decoder framework for multimodal remote sensing segmentation. First, we develop a self-adaptive weighting fusion strategy that employs attention-guided, learnable weighting to dynamically integrate optical and SAR features, enhancing cross-modal complementarity, suppressing redundancy, and producing a unified multimodal representation. Second, we introduce an omnidirectional additive state space block, which leverages eight-directional selective scanning and residual aggregation to capture anisotropic spatial features from an overhead perspective. Finally, a teacher network provides global semantic supervision, guiding the student network toward consistent local-global feature alignment, while a decoder refines structural details for precise segmentation. Extensive experiments on the WHU-OPT-SAR and DDHR-Pohang datasets demonstrate that MNet achieves state-of-the-art performance on both multimodal and unimodal tasks, highlighting the potential of Mamba-based architectures for multimodal remote sensing analysis.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"205 Pt C","pages":"109645"},"PeriodicalIF":7.2,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149076086","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":"Corrigendum to \"BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop\" [Neural Networks, 199 (2026), 108673].","authors":"Chao Chen, Xujia Li, Dongsheng Hong, Shanshan Lin, Xiangwen Liao, Chuanyi Liu, Lei Chen","doi":"10.1016/j.neunet.2026.109116","DOIUrl":"10.1016/j.neunet.2026.109116","url":null,"abstract":"","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"201 ","pages":"109116"},"PeriodicalIF":7.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148007239","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":"AstroHSP: A hybrid supervision framework for robust monocular astronaut pose estimation.","authors":"Haohang Jian, Yuhao Xiao, Xiongwu Xiao, Jianguo Yan, Zhigang Tu","doi":"10.1016/j.neunet.2026.108875","DOIUrl":"10.1016/j.neunet.2026.108875","url":null,"abstract":"<p><p>Accurate 3D human pose estimation is critical for astronaut safety and ergonomic analysis, yet it remains a fundamental challenge under severe deformation, heavy self-occlusion, and extreme domain shift, particularly in the absence of 3D ground-truth annotations. To address this problem, we propose AstroHSP, a robust two-stage framework that integrates domain-adaptive 2D pose estimation with uncertainty-aware 3D pose lifting. In the first stage, a mixed-domain training strategy combined with a novel Domain-Adaptive Batch Normalization mechanism is adopted to achieve stable and consistent 2D keypoint predictions under extreme appearance distortions and severe occlusions. In the second stage, we design an advanced 2D-to-3D lifting module that employs a dual-stream Transformer to model spatio-temporal dependencies and incorporates a conditional diffusion model to iteratively refine coarse 3D poses, thereby effectively modeling and mitigating inherent depth uncertainty. To cope with the practical unavailability of 3D ground truth in highly constrained target domains, we further introduce a two-stage hybrid training strategy, in which the model is first pre-trained with full supervision on public datasets and subsequently fine-tuned through joint optimization that retains full supervision on public data while introducing weak geometric constraints on the target domain. We introduce AstPose, a dataset collected from real space missions, and conduct comprehensive evaluations across multiple datasets, including clothing-heavy and highly constrained scenarios. AstroHSP demonstrates superior performance across multiple datasets, affirming the efficacy of our specialized design for robust 3D pose generalization in highly constrained domains.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"200 ","pages":"108875"},"PeriodicalIF":7.2,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147522590","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":"Transforming tabular data into images for deep learning models","authors":"Abdullah Elen ,&nbsp;Emre Avuçlu","doi":"10.1016/j.neunet.2026.108715","DOIUrl":"10.1016/j.neunet.2026.108715","url":null,"abstract":"<div><div>Deep learning (DL) has achieved remarkable success in processing unstructured data such as images, text, and audio, yet its application to tabular numerical datasets remains challenging due to the lack of inherent spatial structure. In this study, we present a novel approach for transforming numerical tabular data into grayscale image representations, enabling the effective use of convolutional neural networks and other DL architectures on traditionally numerical datasets. The method normalizes features, organizes them into square image matrices, and generates labeled images for classification. Experiments were conducted on four publicly available datasets: Rice MSC Dataset (RMSCD), Optical Recognition of Handwritten Digits (Optdigits), TUNADROMD, and Spambase. Transformed datasets were evaluated using Residual Network (ResNet-18) and Directed Acyclic Graph Neural Network (DAG-Net) models with 5-fold cross-validation. The DAG-Net model achieved accuracies of 99.91% on RMSCD, 99.77% on Optdigits, 98.84% on TUNADROMD, and 93.06% on Spambase, demonstrating the efficacy of the proposed transformation. Additional ablation studies and efficiency analyses highlight improvements in training performance and computational cost. The results indicate that the proposed image-based transformation provides a practical and efficient strategy for integrating numerical datasets into deep learning workflows, broadening the applicability of DL techniques across diverse domains. The implementation is released as open-source software to facilitate reproducibility and further research.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108715"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174306","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":"Gradient-informed neural networks: Embedding prior beliefs for learning in low-data scenarios","authors":"Filippo Aglietti ,&nbsp;Francesco Della Santa ,&nbsp;Andrea Piano ,&nbsp;Virginia Aglietti","doi":"10.1016/j.neunet.2026.108681","DOIUrl":"10.1016/j.neunet.2026.108681","url":null,"abstract":"<div><div>We propose Gradient-Informed Neural Networks (<span>g</span>rad<span>inn</span> s), a methodology that can be used to efficiently approximate a wide range of functions in low-data regimes, when only general prior beliefs are available, a condition that is often encountered in complex engineering problems.</div><div><span>g</span>rad<span>inn</span> s incorporate prior beliefs about the first-order derivatives of the target function to constrain the behavior of its gradient, thus implicitly shaping it, without requiring explicit access to the target function’s derivatives. This is achieved by using two Neural Networks: one modeling the target function and a second, auxiliary network expressing the prior beliefs about the first-order derivatives (e.g., smoothness, oscillations, etc.). A customized loss function enables the training of the first network while enforcing gradient constraints derived from the auxiliary network; at the same time, it allows these constraints to be relaxed in accordance with the training data. Numerical experiments demonstrate the advantages of <span>g</span>rad<span>inn</span> s, particularly in low-data regimes, with results showing strong performance compared to standard Neural Networks across the tested scenarios, including synthetic benchmark functions and real-world engineering tasks.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108681"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146167562","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":"NG-SNN: A neurogenesis-inspired dynamic adaptive framework for efficient spike classification","authors":"Jing Tang ,&nbsp;Depeng Li ,&nbsp;Zhenyu Zhang ,&nbsp;Zhigang Zeng","doi":"10.1016/j.neunet.2026.108656","DOIUrl":"10.1016/j.neunet.2026.108656","url":null,"abstract":"<div><div>Spiking neural networks (SNNs) are designed for low-power neuromorphic computing. A widely adopted hybrid paradigm decouples feature extraction from classification to improve biological plausibility and modularity. However, this decoupling concentrates decision making in the downstream classifier, which in many systems becomes the limiting factor for both accuracy and efficiency. Hand-preset, fixed topologies risk either redundancy or insufficient capacity, and surrogate-gradient training remains computationally costly. Biological neurogenesis is the brain’s mechanism for adaptively adding new neurons to build efficient, task-specific circuits. Inspired by this process, we propose the neurogenesis-inspired spiking neural network (NG-SNN), a dynamic adaptive framework that uses two key innovations to address these challenges. Specifically, we first introduce a supervised incremental construction mechanism that dynamically grows a task-optimal structure by selectively integrating neurons under a contribution criterion. Second, we devise an activity-dependent analytical learning method that replaces iterative optimization with single-shot and adaptive weight computation for each structural update, drastically improving training efficiency. Therefore, NG-SNN uniquely integrates dynamic structural adaptation with efficient non-iterative learning, forming a self-organizing and rapidly converging classification system. Moreover, this neurogenesis-driven process endows NG-SNN with a highly compact structure that requires significantly fewer parameters. Extensive experiments demonstrate that our NG-SNN matches or outperforms its competitors on diverse datasets, without the overhead of iterative training and manual architecture tuning.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108656"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174599","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":"Trainable-parameter-free structural-diversity message passing for graph neural networks","authors":"Mingyue Kong,&nbsp;Yinglong Zhang,&nbsp;Chengda Xu,&nbsp;Xuewen Xia,&nbsp;Xing Xu","doi":"10.1016/j.neunet.2026.108711","DOIUrl":"10.1016/j.neunet.2026.108711","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) have achieved strong performance in structured data modeling such as node classification. However, real-world graphs often exhibit heterogeneous neighborhoods and complex feature distributions, while mainstream approaches rely on many learnable parameters and apply uniform aggregation to all neighbors. This lack of explicit modeling for structural diversity often leads to representation homogenization, semantic degradation, and poor adaptability under challenging conditions such as low supervision or class imbalance. To address these limitations, we propose a trainable-parameter-free graph neural network framework, termed the Structural-Diversity Graph Neural Network (SDGNN), which operationalizes structural diversity in message passing. At its core, the Structural-Diversity Message Passing (SDMP) mechanism performs within-group statistics followed by cross-group selection, thereby capturing neighborhood heterogeneity while stabilizing feature semantics. SDGNN further incorporates complementary structure-driven and feature-driven partitioning strategies, together with a normalized-propagation-based global structural enhancer, to enhance adaptability across diverse graphs. Extensive experiments on nine public benchmark datasets and an interdisciplinary PubMed citation network demonstrate that SDGNN consistently outperforms mainstream GNNs, especially under low supervision, class imbalance, and cross-domain transfer. The full implementation, including code and configurations, is publicly available at: <span><span>https://github.com/mingyue15694/SGDNN/tree/main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108711"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174717","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":"CGLK-GNN : A connectome generation network with large kernels for GNN based Alzheimer’s disease analysis","authors":"Wenqi Zhu ,&nbsp;Zhong Yin ,&nbsp;Yinghua Fu ,&nbsp;Alzheimer's Disease Neuroimaging Initiative","doi":"10.1016/j.neunet.2026.108689","DOIUrl":"10.1016/j.neunet.2026.108689","url":null,"abstract":"<div><div>Alzheimer’s disease (AD) is a currently incurable neurodegenerative disease, with early detection representing a high research priority. AD is characterized by progressive cognitive decline accompanied by alterations in brain functional connectivity. Based on its data structure similar to the graph, graph neural networks (GNNs) have emerged as important methods for brain function analysis and disease prediction in recent years. However, most GNN methods are limited by information loss caused by traditional functional connectivity calculation as well as common noise issues in functional magnetic resonance imaging (fMRI) data. This paper proposes a graph generation based AD classification model using resting state fMRI to address this issue. The connectome generation network with large kernels for GNN (CGLK-GNN) based AD Analysis contains a graph generation block and a GNN prediction block. The graph generation block employs decoupled convolutional networks with large kernels to extract comprehensive temporal features while preserving sequential dependencies, contrasting with previous generative GNN approaches. This module constructs the connectome graph by encoding both edge-wise correlations and node-embedded temporal features, thereby utilizing the generated graph more effectively. The subsequent GNN prediction block adopts an efficient architecture to learn these enhanced representations and perform final AD stage classification. Through independent cohort validations, CGLK-GNN outperforms state-of-the-art GNN and rsfMRI-based AD classifiers in differentiating AD status. Furthermore, CGLK-GNN demonstrates high clinical value by learning clinically relevant connectome node and connectivity features from two independent datasets.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108689"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174719","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":"SCAD: A self-constrained solution to automate context-guided zero-shot image anomaly detection","authors":"Siqi Wang ,&nbsp;Guangpu Wang ,&nbsp;Xinwang Liu ,&nbsp;Jie Liu ,&nbsp;Jiyuan Liu ,&nbsp;Siwei Wang","doi":"10.1016/j.neunet.2026.108577","DOIUrl":"10.1016/j.neunet.2026.108577","url":null,"abstract":"<div><div>Image anomaly detection (IAD) usually requires a separated train set to build an inductive model, which then infers on the test set. However, the cost of collecting and labeling training images has inspired <em>zero-shot IAD</em> (ZS-IAD), which directly processes the test set without the train set. Most ZS-IAD methods resort to pre-trained foundation models (e.g., CLIP), which rely on external prompts and lack adaptation to the target IAD scene. By contrast, <em>context-guided ZS-IAD</em> methods have recently attracted a growing interest: They not only avoid using external prompts by exploiting scene-specific context clues within unlabeled images, but also achieve superior performance to prior ZS-IAD counterparts. Unfortunately, existing context-guided ZS-IAD methods suffer from two vital flaws: The absence of train set forces them to set key hyperparameters blindly, which leads to unreliable performance. Besides, they do not actively handle mixed anomalies that disturb the learning process. To this end, we propose to automate context-guided ZS-IAD by a novel <strong>S</strong>elf-<strong>C</strong>onstrained <strong>A</strong>nomaly <strong>D</strong>etector (SCAD), which makes the following contributions: <strong>(1)</strong> We propose a novel self-constrained mechanism that can automatically determine proper values for key hyperparameters. <strong>(2)</strong> We design a new online self-constrained sampler that terminates the time-consuming sampling process by a proper stopping point, which can significantly reduce the computational cost. <strong>(3)</strong> We develop self-constrained normality refinement strategies that can actively constrain anomalies’ impact and automatically rectify the stopping threshold. To the best of our knowledge, this is also the first work that addresses hyperparameter selection in the IAD realm. Experiments show that SCAD not only yields comparable performance to classic IAD solutions, but also matches ZS-IAD solutions enhanced by hindsight knowledge (i.e., hyperparameters validated on the test set).</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"199 ","pages":"Article 108577"},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146049071","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}