Neural Networks最新文献

Outer synchronization and outer H_∞ synchronization for coupled fractional-order reaction-diffusion neural networks with multiweights. 多权重耦合分数阶反应扩散神经网络的外同步和外 H∞ 同步

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-01-01 Epub Date: 2024-11-09 DOI: 10.1016/j.neunet.2024.106893

Jin-Liang Wang, Si-Yang Wang, Yan-Ran Zhu, Tingwen Huang

引用次数: 0

Enabling deformation slack in tracking with temporally even correlation filters. 利用时间上均匀的相关滤波器实现跟踪中的变形松弛。

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-01-01 Epub Date: 2024-10-29 DOI: 10.1016/j.neunet.2024.106839

Yuanming Zhang, Huihui Pan, Jue Wang

{"title":"Enabling deformation slack in tracking with temporally even correlation filters.","authors":"Yuanming Zhang, Huihui Pan, Jue Wang","doi":"10.1016/j.neunet.2024.106839","DOIUrl":"10.1016/j.neunet.2024.106839","url":null,"abstract":"Discriminative correlation filters with temporal regularization have recently attracted much attention in mobile video tracking, due to the challenges of target occlusion and background interference. However, rigidly penalizing the variability of templates between adjacent frames makes trackers lazy for target evolution, leading to inaccurate responses or even tracking failure when deformation occurs. In this paper, we address the problem of instant template learning when the target undergoes drastic variations in appearance and aspect ratio. We first propose a temporally even model featuring deformation slack, which theoretically supports the ability of the template to respond quickly to variations while suppressing disturbances. Then, an optimal derivation of our model is formulated, and the closed form solutions are deduced to facilitate the algorithm implementation. Further, we introduce a cyclic shift methodology for mirror factors to achieve scale estimation of varying aspect ratios, thereby dramatically improving the cross-area accuracy. Comprehensive comparisons on seven datasets demonstrate our excellent performance: DroneTB-70, VisDrone-SOT2019, VOT-2019, LaSOT, TC-128, UAV-20L, and UAVDT. Our approach runs at 16.9 frames per second on a low-cost Central Processing Unit, which makes it suitable for tracking on drones. The code and raw results will be made publicly available at: https://github.com/visualperceptlab/TEDS.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"181 ","pages":"106839"},"PeriodicalIF":6.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142607187","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}

引用次数: 0

Corrigendum to "Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning" [Neural Networks Volume 178, October (2024), 1-11/106414]]. 海德拉：用于参数高效微调的多头低阶自适应》[《神经网络》第 178 卷，10 月（2024 年），1-11/106414]]更正。

IF 6 1区计算机科学

Neural Networks Pub Date : 2025-01-01 Epub Date: 2024-11-15 DOI: 10.1016/j.neunet.2024.106878

Sanghyeon Kim, Hyunmo Yang, Younghyun Kim, Youngjoon Hong, Eunbyung Park

引用次数: 0

Adaptive discrete-time neural prescribed performance control: A safe control approach. 自适应离散时间神经规定性能控制：安全控制方法

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-16 DOI: 10.1016/j.neunet.2024.107025

Zhonghua Wu, Bo Huang, Xiangwei Bu

{"title":"Adaptive discrete-time neural prescribed performance control: A safe control approach.","authors":"Zhonghua Wu, Bo Huang, Xiangwei Bu","doi":"10.1016/j.neunet.2024.107025","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107025","url":null,"abstract":"Most existing results on prescribed performance control (PPC), subject to input saturation and initial condition limitations, focus on continuous-time nonlinear systems. This article, as regards discrete-time nonlinear systems, is dedicated to constructing a novel adaptive switching control strategy to circumvent the singular problem when the PPC undergoes input saturation, while the initial conditions of the system can be released under the framework of PPC. The main design steps and characteristics include: (1) By devising a new discrete-time global finite-time performance function (DTGFTPF), the constructed performance boundary is shown to survive insensitive to arbitrary initial values, which present in the system; (2) A discrete-time adaptive finite-time prescribed performance controller (DTAFPPC) and a discrete-time adaptive backstepping controller (DTABC) are constructed, simultaneously. The DTAFPPC possesses the capability to drive tracking error convergence within preset boundaries within a finite time. In the presence of input saturation, the DTABC is applied to prevent system instability while permitting tracking error to occasionally exceed performance bounds without compromising overall stability; and (3) To overcome non-causal problems inherent in backstepping designs, the current moment values of the errors are integrated into the controllers and the adaptive update laws. The stability of the closed-loop system is validated through Lyapunov analysis theory and simulations.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107025"},"PeriodicalIF":6.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142848267","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}

引用次数: 0

Disentangled latent energy-based style translation: An image-level structural MRI harmonization framework.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-16 DOI: 10.1016/j.neunet.2024.107039

Mengqi Wu, Lintao Zhang, Pew-Thian Yap, Hongtu Zhu, Mingxia Liu

{"title":"Disentangled latent energy-based style translation: An image-level structural MRI harmonization framework.","authors":"Mengqi Wu, Lintao Zhang, Pew-Thian Yap, Hongtu Zhu, Mingxia Liu","doi":"10.1016/j.neunet.2024.107039","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107039","url":null,"abstract":"Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from non-biological variations such as differences in field strength and scanner vendors. Numerous retrospective MRI harmonization techniques have demonstrated encouraging outcomes in reducing the site effects at image level. However, existing methods generally suffer from high computational requirements and limited generalizability, restricting their applicability to unseen MRIs. In this paper, we design a novel disentangled latent energy-based style translation (DLEST) framework for unpaired image-level MRI harmonization, consisting of (a) site-invariant image generation (SIG), (b) site-specific style translation (SST), and (c) site-specific MRI synthesis (SMS). Specifically, the SIG employs a latent autoencoder to encode MRIs into a low-dimensional latent space and reconstruct MRIs from latent codes. The SST utilizes an energy-based model to comprehend global latent distribution of a target domain and translate source latent codes towards the target domain, while SMS enables MRI synthesis with a target-specific style. By disentangling image generation and style translation in latent space, the DLEST can achieve efficient style translation. Our model was trained on T1-weighted MRIs from a public dataset (with 3,984 subjects across 58 acquisition sites/settings) and validated on an independent dataset (with 9 traveling subjects scanned in 11 sites/settings) in four tasks: histogram and feature visualization, site classification, brain tissue segmentation, and site-specific structural MRI synthesis. Qualitative and quantitative results demonstrate the superiority of our method over several state-of-the-arts.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107039"},"PeriodicalIF":6.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866115","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}

引用次数: 0

Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-16 DOI: 10.1016/j.neunet.2024.107028

Delong Liu, Haiwen Li, Zhicheng Zhao, Yuan Dong

{"title":"Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval.","authors":"Delong Liu, Haiwen Li, Zhicheng Zhao, Yuan Dong","doi":"10.1016/j.neunet.2024.107028","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107028","url":null,"abstract":"The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and textual modalities. The prevailing methods map texts and images into unified embedding space for matching, while the intricate semantic correspondences between texts and images are still not effectively constructed. To address this issue, we propose a novel TIPR framework to build fine-grained interactions and alignment between person images and the corresponding texts. Specifically, via fine-tuning the Contrastive Language-Image Pre-training (CLIP) model, a visual-textual dual encoder is firstly constructed, to preliminarily align the image and text features. Secondly, a Text-guided Image Restoration (TIR) auxiliary task is proposed to map abstract textual entities to specific image regions, improving the alignment between local textual and visual embeddings. Additionally, a cross-modal triplet loss is presented to handle hard samples, and further enhance the model's discriminability for minor differences. Moreover, a pruning-based text data augmentation approach is proposed to enhance focus on essential elements in descriptions, thereby avoiding excessive model attention to less significant information. The experimental results show our proposed method outperforms state-of-the-art methods on three popular benchmark datasets, and the code will be made publicly available at https://github.com/Delong-liu-bupt/SEN.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107028"},"PeriodicalIF":6.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866126","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}

引用次数: 0

Passivity and robust passivity of inertial memristive neural networks with time-varying delays via non-reduced order method.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-16 DOI: 10.1016/j.neunet.2024.107042

Weizhe Xu, Zihao Li, Song Zhu

引用次数: 0

Dynamic graph consistency and self-contrast learning for semi-supervised medical image segmentation.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-15 DOI: 10.1016/j.neunet.2024.107063

Gang Li, Jinjie Xie, Ling Zhang, Guijuan Cheng, Kairu Zhang, Mingqi Bai

{"title":"Dynamic graph consistency and self-contrast learning for semi-supervised medical image segmentation.","authors":"Gang Li, Jinjie Xie, Ling Zhang, Guijuan Cheng, Kairu Zhang, Mingqi Bai","doi":"10.1016/j.neunet.2024.107063","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107063","url":null,"abstract":"Semi-supervised medical image segmentation endeavors to exploit a limited set of labeled data in conjunction with a substantial corpus of unlabeled data, with the aim of training models that can match or even exceed the efficacy of fully supervised segmentation models. Despite the potential of this approach, most existing semi-supervised medical image segmentation techniques that employ consistency regularization predominantly focus on spatial consistency at the image level, often neglecting the crucial role of feature-level channel information. To address this limitation, we propose an innovative method that integrates graph convolutional networks with a consistency regularization framework to develop a dynamic graph consistency approach. This method imposes channel-level constraints across different decoders by leveraging high-level features within the network. Furthermore, we introduce a novel self-contrast learning strategy, which performs image-level comparison within the same batch and engages in pixel-level contrast learning based on pixel positions. This approach effectively overcomes traditional contrast learning challenges related to identifying positive and negative samples, reduces computational resource consumption, and significantly improves model performance. Our experimental evaluation on three distinct medical image segmentation datasets indicates that the proposed method demonstrates superior performance across a variety of test scenarios.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107063"},"PeriodicalIF":6.0,"publicationDate":"2024-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866117","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}

引用次数: 0

A fully value distributional deep reinforcement learning framework for multi-agent cooperation.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-14 DOI: 10.1016/j.neunet.2024.107035

Mingsheng Fu, Liwei Huang, Fan Li, Hong Qu, Chengzhong Xu

{"title":"A fully value distributional deep reinforcement learning framework for multi-agent cooperation.","authors":"Mingsheng Fu, Liwei Huang, Fan Li, Hong Qu, Chengzhong Xu","doi":"10.1016/j.neunet.2024.107035","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107035","url":null,"abstract":"Distributional Reinforcement Learning (RL) extends beyond estimating the expected value of future returns by modeling its entire distribution, offering greater expressiveness and capturing deeper insights of the value function. To leverage this advantage, distributional multi-agent systems based on value-decomposition techniques were proposed recently. Ideally, a distributional multi-agent system should be fully distributional, which means both the individual and global value functions should be constructed in distributional forms. However, recent studies show that directly applying traditional value-decomposition techniques to this fully distributional form cannot guarantee the satisfaction of the necessary individual-global-max (IGM) principle. To address this problem, we propose a novel fully value distributional multi-agent framework based on value-decomposition and prove that the IGM principle can be guaranteed under our framework. Based on this framework, a practical deep reinforcement learning model called Fully Distributional Multi-Agent Cooperation (FDMAC) is proposed, and the effectiveness of FDMAC is verified under different scenarios of the StarCraft Multi-Agent Challenge micromanagement environment. Further experimental results show that our FDMAC model can outperform the best baseline by 10.47% on average in terms of the median test win rate.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107035"},"PeriodicalIF":6.0,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142856374","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}

引用次数: 0

Rethinking the optimization objective for transferable adversarial examples from a fuzzy perspective.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-12-13 DOI: 10.1016/j.neunet.2024.107019

Xiangyuan Yang, Jie Lin, Hanlin Zhang, Peng Zhao

{"title":"Rethinking the optimization objective for transferable adversarial examples from a fuzzy perspective.","authors":"Xiangyuan Yang, Jie Lin, Hanlin Zhang, Peng Zhao","doi":"10.1016/j.neunet.2024.107019","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.107019","url":null,"abstract":"Transferable adversarial examples, which are generated by transfer-based attacks, have strong adaptability for attacking a completely unfamiliar victim model without knowing its architecture, parameters and outputs. While current transfer-based attacks easily defeat surrogate model with minor perturbations, they struggle to transfer these perturbations to unfamiliar victim models. To characterize these untransferable adversarial examples, which consist of natural examples and perturbations, we define the concept of fuzzy domain. Here, the adversarial examples that do not fall inside the fuzzy domain will successfully attack the victim model. To assist the adversarial examples in escaping from the fuzzy domain, we propose a fuzzy optimization-based transferable attack (FOTA) to maximize both the original cross-entropy (CE) loss and the newly proposed membership functions. The proposed membership functions are positively correlated to the probability of falling outside the fuzzy domain. Furthermore, to maximize the transferability of adversarial examples, we present Adaptive FOTA (Ada-FOTA), which dynamically updates the adversarial examples until the membership functions converge, rather than fixing the number of update iterations in advance in the current attacks. When the membership functions converge to 1, the maximum probability that adversarial examples fall outside the fuzzy domain can be achieved. The empirical results on ImageNet dataset show that, for minor perturbations, our FOTA can improve the transferability of adversarial examples by 5.4% on attacking five naturally-trained victim models, and Ada-FOTA can further increase the transferability of adversarial examples by an additional 13.8% in comparison with current transfer-based attacks. Code is available at https://github.com/HaloMoto/FOTA.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"107019"},"PeriodicalIF":6.0,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142866123","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}

引用次数: 0