Neurocomputing最新文献_第4页

Imperceptible rhythm backdoor attacks: Exploring rhythm transformation for embedding undetectable vulnerabilities on speech recognition 不可察觉的节奏后门攻击：探索在语音识别中嵌入不可察觉漏洞的节奏变换

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-28 DOI: 10.1016/j.neucom.2024.128779

Wenhan Yao , Jiangkun Yang , Yongqiang He , Jia Liu , Weiping Wen

{"title":"Imperceptible rhythm backdoor attacks: Exploring rhythm transformation for embedding undetectable vulnerabilities on speech recognition","authors":"Wenhan Yao , Jiangkun Yang , Yongqiang He , Jia Liu , Weiping Wen","doi":"10.1016/j.neucom.2024.128779","DOIUrl":"10.1016/j.neucom.2024.128779","url":null,"abstract":"<div><div>Speech recognition is an essential start ring of human–computer interaction. Recently, deep learning models have achieved excellent success in this task. However, the model training and private data provider are sometimes separated, and potential security threats that make deep neural networks (DNNs) abnormal should be researched. In recent years, the typical threats, such as backdoor attacks, have been analysed in speech recognition systems. The existing backdoor methods are based on data poisoning. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, such as pitch and timbre. As a result, the poisoned data can be detected by human hearing or automatic deep algorithms. To improve the stealthiness of data poisoning, we propose a non-neural and fast algorithm called <strong>R</strong>andom <strong>S</strong>pectrogram <strong>R</strong>hythm <strong>T</strong>ransformation (RSRT) in this paper. The algorithm combines four steps to generate stealthy poisoned utterances. From the perspective of rhythm component transformation, our proposed trigger stretches or squeezes the mel spectrograms and recovers them back to signals. The operation keeps timbre and content unchanged for good stealthiness. Our experiments are conducted on two kinds of speech recognition tasks, including testing the stealthiness of poisoned samples by speaker verification and automatic speech recognition. The results show that our method is effective and stealthy. The rhythm trigger needs a low poisoning rate and gets a very high attack success rate.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Perceptual metric for face image quality with pixel-level interpretability 具有像素级可解释性的人脸图像质量感知指标

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-28 DOI: 10.1016/j.neucom.2024.128780

Byungho Jo , In Kyu Park , Sungeun Hong

{"title":"Perceptual metric for face image quality with pixel-level interpretability","authors":"Byungho Jo , In Kyu Park , Sungeun Hong","doi":"10.1016/j.neucom.2024.128780","DOIUrl":"10.1016/j.neucom.2024.128780","url":null,"abstract":"<div><div>This paper tackles the shortcomings of image evaluation metrics in evaluating facial image quality. Conventional metrics do neither accurately reflect the unique attributes of facial images nor correspond with human visual perception. To address these issues, we introduce a novel metric designed specifically for faces, utilizing a learning-based adversarial framework. This framework comprises a generator for simulating face restoration and a discriminator for quality evaluation. Drawing inspiration from facial neuroscience studies, our metric emphasizes the importance of primary facial features, acknowledging that minor changes in the eyes, nose, and mouth can significantly impact perception. Another key limitation of existing image evaluation metrics is their focus on numerical values at the image level, without providing insight into how different areas of the image contribute to the overall assessment. Our proposed metric offers interpretability regarding how each region of the image is evaluated. Comprehensive experimental results confirm that our face-specific metric surpasses traditional general image quality assessment metrics for facial images, including both full-reference and no-reference methods. The code and models are available at <span><span>https://github.com/AIM-SKKU/IFQA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Implicit expression recognition enhanced table-filling for aspect sentiment triplet extraction 隐式表达识别增强了表格填充功能，可用于方面情感三元组提取

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-26 DOI: 10.1016/j.neucom.2024.128776

Yanbo Li , Qing He , Nisuo Du , Qingni He

{"title":"Implicit expression recognition enhanced table-filling for aspect sentiment triplet extraction","authors":"Yanbo Li , Qing He , Nisuo Du , Qingni He","doi":"10.1016/j.neucom.2024.128776","DOIUrl":"10.1016/j.neucom.2024.128776","url":null,"abstract":"<div><div>Aspect sentiment triplet extraction (ASTE) is a challenging task in aspect-based sentiment analysis (ABSA), involving the identification of aspect terms, opinion terms, and their corresponding sentiment polarities within comments to form triplets. The emergence of more realistic DMASTE datasets, featuring diverse domains, implicit aspect terms, and longer comments, poses challenges for existing methods. In particular, these methods struggle with recognizing implicit expressions effectively and capturing sufficient information. To overcome these hurdles, we propose an implicit expression recognition enhanced table-filling (IERET) method. This approach integrates modeling of overall implicit expression in sentences and employs a bidirectional information aggregation module to capture word pair information comprehensively. During the decoding process, a table-filling method accurately delineates aspect-opinion pair boundaries. Experimental results across in-domain, single-source cross-domain, and multi-source cross-domain on the DMASTE dataset demonstrate that our proposed IERET method achieves state-of-the-art performance.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Industrial and medical anomaly detection through cycle-consistent adversarial networks 通过循环一致性对抗网络进行工业和医疗异常检测

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-26 DOI: 10.1016/j.neucom.2024.128762

Arnaud Bougaham , Valentin Delchevalerie , Mohammed El Adoui , Benoît Frénay

{"title":"Industrial and medical anomaly detection through cycle-consistent adversarial networks","authors":"Arnaud Bougaham , Valentin Delchevalerie , Mohammed El Adoui , Benoît Frénay","doi":"10.1016/j.neucom.2024.128762","DOIUrl":"10.1016/j.neucom.2024.128762","url":null,"abstract":"<div><div>In this study, a new Anomaly Detection (AD) approach for industrial and medical images is proposed. This method leverages the theoretical strengths of unsupervised learning and the data availability of both normal and abnormal classes. Indeed, the AD is often formulated as an unsupervised task, implying only normal images during training. These normal images are devoted to be reconstructed through an autoencoder architecture, for instance. However, the information contained in abnormal data, when available, is also valuable for this reconstruction. The model would be able to identify its weaknesses by also learning how to transform an abnormal image into a normal one. This abnormal-to-normal reconstruction helps the entire model to learn better than a single normal-to-normal reconstruction. To be able to exploit abnormal images, the proposed method uses Cycle-Generative Adversarial Networks (Cycle-GAN) for (ab)normal-to-normal translation. After an input image has been reconstructed by the normal generator, an anomaly score quantifies the differences between the input and its reconstruction. Based on a threshold set to satisfy a business quality constraint, the input image is then flagged as normal or not. The proposed method is evaluated on industrial and medical datasets. The results demonstrate accurate performance with a zero false negative constraint compared to state-of-the-art methods. Quantitatively, our method reaches an accuracy under a zero false negative constraint of 79.89%, representing an improvement of about 17% compared to competitors. The code is available at <span><span>https://github.com/ValDelch/CycleGANS-AnomalyDetection</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Mixed-scale cross-modal fusion network for referring image segmentation 用于参考图像分割的混合尺度跨模态融合网络

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-26 DOI: 10.1016/j.neucom.2024.128793

Xiong Pan , Xuemei Xie , Jianxiu Yang

引用次数: 0

VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering VG-CALF：医学视觉问题解答中用于放射学图像的视觉引导交叉注意和后期融合网络

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-24 DOI: 10.1016/j.neucom.2024.128730

Aiman Lameesa , Chaklam Silpasuwanchai , Md. Sakib Bin Alam

{"title":"VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering","authors":"Aiman Lameesa , Chaklam Silpasuwanchai , Md. Sakib Bin Alam","doi":"10.1016/j.neucom.2024.128730","DOIUrl":"10.1016/j.neucom.2024.128730","url":null,"abstract":"<div><div>Image and question matching is essential in Medical Visual Question Answering (MVQA) in order to accurately assess the visual-semantic correspondence between an image and a question. However, the recent state-of-the-art methods focus solely on the contrastive learning between an entire image and a question. Though contrastive learning successfully model the global relationship between an image and a question, it is less effective to capture the fine-grained alignments conveyed between image regions and question words. In contrast, large-scale pre-training poses significant drawbacks, including extended training times, handling substantial data volumes, and necessitating high computational power. To address these challenges, we propose the Vision-Guided Cross-Attention based Late Fusion (VG-CALF) network, which integrates image and question features into a unified deep model without relying on pre-training for MVQA tasks. In our proposed approach, we use self-attention to effectively leverage intra-modal relationships within each modality and implement vision-guided cross-attention to emphasize the inter-modal relationships between image regions and question words. By simultaneously considering intra-modal and inter-modal relationships, our proposed method significantly improves the overall performance of MVQA without the need for pre-training on extensive image-question pairs. Experimental results on benchmark datasets, such as, SLAKE and VQA-RAD demonstrate that our proposed approach performs competitively with existing state-of-the-art methods.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Synchronization of nonlinear neural networks with hybrid couplings and uncertain time-varying perturbations: A novel distributed-delay impulsive comparison principle 具有混合耦合和不确定时变扰动的非线性神经网络的同步：新型分布式延迟脉冲比较原理

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-24 DOI: 10.1016/j.neucom.2024.128729

Hongguang Fan , Kaibo Shi , Yi Zhao

引用次数: 0

FedATA: Adaptive attention aggregation for federated self-supervised medical image segmentation FedATA：联合自监督医学图像分割的自适应注意力聚合

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-22 DOI: 10.1016/j.neucom.2024.128691

Jian Dai , Hao Wu , Huan Liu , Liheng Yu , Xing Hu , Xiao Liu , Daoying Geng

{"title":"FedATA: Adaptive attention aggregation for federated self-supervised medical image segmentation","authors":"Jian Dai , Hao Wu , Huan Liu , Liheng Yu , Xing Hu , Xiao Liu , Daoying Geng","doi":"10.1016/j.neucom.2024.128691","DOIUrl":"10.1016/j.neucom.2024.128691","url":null,"abstract":"<div><div>Pre-trained on large-scale datasets has profoundly promoted the development of deep learning models in medical image analysis. For medical image segmentation, collecting a large number of labeled volumetric medical images from multiple institutions is an enormous challenge due to privacy concerns. Self-supervised learning with mask image modeling (MIM) can learn general representation without annotations. Integrating MIM into FL enables collaborative learning of an efficient pre-trained model from unlabeled data, followed by fine-tuning with limited annotations. However, setting pixels as reconstruction targets in traditional MIM fails to facilitate robust representation learning due to the medical image's complexity and distinct characteristics. On the other hand, the generalization of the aggregated model in FL is also impaired under the heterogeneous data distributions among institutions. To address these issues, we proposed a novel self-supervised federated learning, which combines masked self-distillation with adaptive attention federated learning. Such incorporation enjoys two vital benefits. First, masked self-distillation sets high-quality latent representations of masked tokens as the target, improving the descriptive capability of the learned presentation rather than reconstructing low-level pixels. Second, adaptive attention aggregation with Personalized federate learning effectively captures specific-related representation from the aggregated model, thus facilitating local fine-tuning performance for target tasks. We conducted comprehensive experiments on two medical segmentation tasks using a large-scale dataset consisting of volumetric medical images from multiple institutions, demonstrating superior performance compared to existing federated self-supervised learning approaches.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Easy and effective! Data augmentation for knowledge-aware dialogue generation via multi-perspective sentences interaction 简单有效！通过多视角句子交互为知识感知对话生成进行数据扩增

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-22 DOI: 10.1016/j.neucom.2024.128724

Sisi Peng , Dan Qu , Wenlin Zhang , Hao Zhang , Shunhang Li , Minchen Xu

{"title":"Easy and effective! Data augmentation for knowledge-aware dialogue generation via multi-perspective sentences interaction","authors":"Sisi Peng , Dan Qu , Wenlin Zhang , Hao Zhang , Shunhang Li , Minchen Xu","doi":"10.1016/j.neucom.2024.128724","DOIUrl":"10.1016/j.neucom.2024.128724","url":null,"abstract":"<div><div>In recent years, knowledge-based dialogue generation has garnered significant attention due to its capacity to produce informative and coherent responses through the integration of external knowledge into models. However, obtaining high-quality knowledge that aligns with the dialogue content poses a considerable challenge, necessitating substantial time and resources. To tackle the issue of limited dialogue data, a majority of research endeavors concentrate on data augmentation to augment the volume of training data. Regrettably, these methods overlook knowledge augmentation, leading to a restricted diversity in input data and yielding enhancements solely in specific metrics. Real-world conversations exhibit a spectrum of characteristics, including repetitions, reversals, and interruptions, demanding a heightened level of data diversity. In this study, we introduce a straightforward yet effective data augmentation technique known as Multi-perspective Sentence Interaction to bolster the connections among sentences from varied viewpoints. Through an examination of target responses from multiple dialogue perspectives, we enhance our comprehension of the relationships between dialogue sentences, thereby facilitating the expansion of knowledge-based dialogue data. Through experiments conducted on various knowledge-based dialogue datasets and utilizing different models, our findings illustrate a notable enhancement in the quality of model generation facilitated by our method. Specifically, we observed a 3.5% enhancement in reply accuracy and a 0.1506 increase in diversity (DIST-2). Moreover, there was a substantial improvement in knowledge selection accuracy by 19.04% and a reduction in model perplexity by 31.48%.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Answering, Fast and Slow: Strategy enhancement of visual understanding guided by causality 回答，快与慢》：因果关系引导下的视觉理解策略提升

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2024-10-22 DOI: 10.1016/j.neucom.2024.128735

Chao Wang , Zihao Wang , Yang Zhou

引用次数: 0