Knowledge-Based Systems最新文献_第8页

Development of a runtime-condition model for proactive intelligent products using knowledge graphs and embedding 利用知识图和嵌入技术开发主动智能产品的运行状态模型

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-15 DOI: 10.1016/j.knosys.2025.113484

Fan Mo , Hamood Ur Rehman , Miriam Ugarte , Angela Carrera-Rivera , Nathaly Rea Minango , Fabio Marco Monetti , Antonio Maffei , Jack C. Chaplin

{"title":"Development of a runtime-condition model for proactive intelligent products using knowledge graphs and embedding","authors":"Fan Mo , Hamood Ur Rehman , Miriam Ugarte , Angela Carrera-Rivera , Nathaly Rea Minango , Fabio Marco Monetti , Antonio Maffei , Jack C. Chaplin","doi":"10.1016/j.knosys.2025.113484","DOIUrl":"10.1016/j.knosys.2025.113484","url":null,"abstract":"<div><div>Modern manufacturing processes’ increasing complexity and variability demand advanced systems capable of real-time monitoring, adaptability, and data-driven decision-making. This paper introduces a novel runtime condition model to enhance interoperability, data integration, and decision support within intelligent manufacturing environments. The model encapsulates key manufacturing elements, including asset management, relationships, key performance indicators (KPIs), capabilities, data structures, constraints, and configurations. A key innovation is the integration of a knowledge graph enriched with embedding techniques, enabling the inference of missing relationships, dynamic reasoning, and predictive analytics.</div><div>The proposed model was validated through a case study conducted in collaboration with TQC Automation Ltd., using their MicroApplication Leak Test System (MALT). A dataset of over 9,000 unique test configurations demonstrated the model’s capabilities in representing runtime conditions, managing operational parameters, and optimising test configurations. The enriched knowledge graph facilitated advanced analyses, providing actionable insights into test outcomes and enabling proactive decision-making.</div><div>Empirical results showcase the model’s ability to harmonise diverse data sources, infer missing connections, and improve runtime adaptability. This study highlights the potential of combining runtime modelling with knowledge graphs to address the challenges of modern manufacturing. Future research will explore the model’s application to additional domains, integration with larger datasets, and the use of machine learning for enhanced predictive capabilities.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113484"},"PeriodicalIF":7.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860423","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

FDC-Swap: An efficient face swapping framework based on feature disentangling consistency FDC-Swap：一种基于特征解缠一致性的高效人脸交换框架

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-15 DOI: 10.1016/j.knosys.2025.113457

Jue Tian , Chunya Zhao , Yang Liu , Yanping Chen

{"title":"FDC-Swap: An efficient face swapping framework based on feature disentangling consistency","authors":"Jue Tian , Chunya Zhao , Yang Liu , Yanping Chen","doi":"10.1016/j.knosys.2025.113457","DOIUrl":"10.1016/j.knosys.2025.113457","url":null,"abstract":"<div><div>Face swapping images with high quality are critical for video production, privacy protection, and forgery detection, etc. In face swapping technology, one kernel element is the disentanglement of identity and attribute information. However, due to their deep entanglement in the latent space, effectively enhancing disentangling ability remains challenging. To tackle this challenge, this paper proposes the feature disentangling consistency: by executing the face swapping process (i.e., disentangling and recombining the identity and attribute information of two face images) in a pipeline twice, the generated twice-swapped images should be consistent with the original images. First, a new evaluation method (named FDC-Evaluation) is proposed to assess model performance according to disentangling consistency, which can be reflected in identity-attribute or image-level consistency. Meanwhile, to handle the limitation of missing ground truth, we introduce the FDC-Evaluation into original face swapping network, and propose a highly scalable and lightweight swapping framework (named FDC-Swap). Experiments demonstrate that the FDC-Evaluation overcomes traditional evaluation limitations, such as cognitive differences in identity-attribute features, identity assessment unfairness due to choices of identity encoders in training and evaluation, and operational complexity due to attribute feature diversity. Meanwhile, the FDC-Swap framework effectively enhances the performance of various existing face swapping networks. Code available at <span><span>https://github.com/tzjoyzx/FDC_Swap</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113457"},"PeriodicalIF":7.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870736","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

Evolutionary Bayesian Optimization for automated circuit sizing 自动化电路尺寸的进化贝叶斯优化

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-15 DOI: 10.1016/j.knosys.2025.113483

Cătălin Vişan , Mihai Boldeanu , Georgian Nicolae , Horia Cucu , Corneliu Burileanu , Andi Buzo

{"title":"Evolutionary Bayesian Optimization for automated circuit sizing","authors":"Cătălin Vişan , Mihai Boldeanu , Georgian Nicolae , Horia Cucu , Corneliu Burileanu , Andi Buzo","doi":"10.1016/j.knosys.2025.113483","DOIUrl":"10.1016/j.knosys.2025.113483","url":null,"abstract":"<div><div>Automated circuit sizing using Artificial Intelligence is a rapidly increasing area of interest, primarily thanks to its potential to accelerate product time-to-market and enhance employee satisfaction. A host of methods, rooted in different fundamental research philosophies, have been devised for this class of problems. While some of them perform well in terms of convergence speed, robustness has generally been given less attention. In this study we propose a novel automatic circuit sizing framework called Evolutionary Bayesian Optimization (EBO). It is a hybrid method combining the strengths of evolutionary computation techniques and Bayesian Optimization. EBO takes full advantage of parallel simulation infrastructure, by inherently using large batches of simulations. Our method is especially designed for multi-objective problems. Thus, it can optimize a large variety of circuits without the need of constructing figure of merit functions. Moreover, the strong emphasis on exploring the high-dimensional space of design variables ensures that EBO is robust and reliable across varying levels of problem complexity. We compare our framework with two state-of-the-art methods having different underlying philosophies and with arguably the most promising multi-objective evolutionary algorithm for this class of problems on four circuits: two proprietary voltage regulators, an open-source voltage regulator, and an open-source operational amplifier. The results show that EBO is superior to the other considered methods with regard to convergence speed and robustness. Generally, it can save between 30% and 70% circuit simulations compared to the next best performing method. Furthermore, EBO is the only method that finds circuit configurations that meet the specifications for all the considered circuits.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113483"},"PeriodicalIF":7.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843959","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

Graph-based predictable deep transfer network for soft sensing of dynamic industrial processes 动态工业过程软测量的基于图的可预测深度传递网络

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-15 DOI: 10.1016/j.knosys.2025.113495

Zhengxuan Zhang , Xu Yang , Jian Huang , Yuri A.W. Shardt

{"title":"Graph-based predictable deep transfer network for soft sensing of dynamic industrial processes","authors":"Zhengxuan Zhang , Xu Yang , Jian Huang , Yuri A.W. Shardt","doi":"10.1016/j.knosys.2025.113495","DOIUrl":"10.1016/j.knosys.2025.113495","url":null,"abstract":"<div><div>Due to their advantages in high-level abstract feature extraction, stacked auto-encoders and their supervisory variants have been widely used to develop soft sensors for industrial processes. However, since they fail to provide analytical solutions for the autoregression embedded in networks, the difficulty in modeling the temporal correlation in latent features of supervisory stacked auto-encoders greatly increases. Moreover, the normal assumption for the design of soft sensors of an independent, identical distribution does not hold when there are changes in the training and testing data. Thus, a graph-based, predictable, deep transfer network (GPDTN) for soft sensing of dynamic industrial processes is proposed. To effectively learn the dynamic information of past data, a new loss function is proposed to reconstruct the data and simultaneously learn the predictable latent space using joint mutual information and graph embedding. Then, using deep domain adaptation, a new regular term of dynamic alignment is added to narrow the differences of the predictive information between source and target domains, enabling the graph-based predictable structure to be adaptable to concept drift in dynamic processes. Finally, the performance and effectiveness of the GPDTN-based soft sensors are demonstrated through experimental results on the industrial debutanizer and sulfur recovery unit.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113495"},"PeriodicalIF":7.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851358","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

Joint multi-layer network and coupling redundancy minimization for semi-supervised EEG-based emotion recognition 基于半监督脑电图的情感识别联合多层网络及耦合冗余最小化

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-15 DOI: 10.1016/j.knosys.2025.113559

Liangliang Hu , Daowen Xiong , Congming Tan , Zhentao Huang , Yikang Ding , Jiahao Jin , Yin Tian

{"title":"Joint multi-layer network and coupling redundancy minimization for semi-supervised EEG-based emotion recognition","authors":"Liangliang Hu , Daowen Xiong , Congming Tan , Zhentao Huang , Yikang Ding , Jiahao Jin , Yin Tian","doi":"10.1016/j.knosys.2025.113559","DOIUrl":"10.1016/j.knosys.2025.113559","url":null,"abstract":"<div><div>Processing high-level cognitive functions like emotion involves dynamic interaction among multiple brain regions. Interactions involving within- and cross-frequency couplings across these regions are paramount in supporting brain functions. Existing emotion recognition models predominantly focus on within-frequency couplings. However, they lack the incorporation of cross-frequency couplings and within-frequency interactions, essential for providing a comprehensive representation of emotional states. To address this limitation, we propose a novel semi-supervised model for emotion recognition that incorporates a multi-layer network and coupling redundancy minimization (JMNCRM) into a unified framework. First, we construct a generalized multi-layer network that embeds rich coupling information about within- and cross-frequency couplings through cosine similarity of features. Then, without increasing the feature dimensionality, the multi-layer network is incorporated into a discriminative linear regression model as a redundant minimum regularization term. During the optimization process, our model selects the most discriminative and non-redundant feature subsets for emotion recognition while retaining the rich structural, discriminative, and coupling information of electroencephalogram (EEG) data in the learned projection subspace. Extensive experimental results on two public datasets and our music-evoked emotion dataset demonstrate that the JMNCRM model outperforms other state-of-the-art algorithms regarding classification performance. Additionally, the intrinsic activation patterns revealed by JMNCRM are consistent with emotional cognition. The code for JMNCRM will be available at <span><span>https://github.com/czxyhll/JMNCRM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113559"},"PeriodicalIF":7.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851980","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 modified black-winged kite optimizer based on chaotic maps for global optimization of real-world applications 一种基于混沌映射的改进黑翼风筝优化器，用于实际应用的全局优化

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-14 DOI: 10.1016/j.knosys.2025.113558

Hanaa Mansouri , Karim Elkhanchouli , Nawal Elghouate , Ahmed Bencherqui , Mohamed Amine Tahiri , Hicham Karmouni , Mhamed Sayyouri , Hassane Moustabchir , S.S. Askar , Mohamed Abouhawwash

{"title":"A modified black-winged kite optimizer based on chaotic maps for global optimization of real-world applications","authors":"Hanaa Mansouri , Karim Elkhanchouli , Nawal Elghouate , Ahmed Bencherqui , Mohamed Amine Tahiri , Hicham Karmouni , Mhamed Sayyouri , Hassane Moustabchir , S.S. Askar , Mohamed Abouhawwash","doi":"10.1016/j.knosys.2025.113558","DOIUrl":"10.1016/j.knosys.2025.113558","url":null,"abstract":"<div><div>Optimization algorithms play a critical role in solving complex engineering and medical imaging optimization problems. However, existing metaheuristic techniques often suffer from premature convergence, inefficient exploration, and imbalance between exploration and exploitation. To address these limitations, this paper proposes the Modified Black-Winged Kite Optimizer (M-BWKO), an enhanced version of the standard BWKO algorithm. M-BWKO incorporates six key improvements: a top-k elite leader strategy, adaptive chaos weighting, diversity-aware chaos reactivation, chaotic index-based selection, adaptive Cauchy mutation, and a hybrid migration rule combining chaotic perturbations, Cauchy mutation, and directional updates. The selected M-BWKO variant, Tent-BWKO (TT-BWKO), is evaluated on the CEC-2022 benchmark suite, achieving up to 22.04 % improvement over BWKO and 99.99 % over other state-of-the-art optimizers, with average gains of 6.30 % and 22.13 %, respectively. These results are statistically validated using the Wilcoxon rank-sum test (<em>p</em> < 0.05), confirming the robustness of the approach. TT-BWKO is further tested on real-world engineering design problems—including Welded Beam, Tension/Compression Spring, and Pressure Vessel—resulting in notable reductions in material cost. It also performs effectively on large-scale Traveling Salesman Problem instances (100, 150, 200 cities), demonstrating strong route optimization and stability. In medical image segmentation, TT-BWKO yields superior PSNR, SSIM, and FSIM scores, confirming its versatility and effectiveness across diverse domains.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113558"},"PeriodicalIF":7.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860512","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

Crop-paste and diffusion-based semi-supervised segmentation network for metal defect detection 基于作物膏体和扩散的金属缺陷半监督分割网络

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-14 DOI: 10.1016/j.knosys.2025.113573

Lixiang Zhao, Jianbo Yu

{"title":"Crop-paste and diffusion-based semi-supervised segmentation network for metal defect detection","authors":"Lixiang Zhao, Jianbo Yu","doi":"10.1016/j.knosys.2025.113573","DOIUrl":"10.1016/j.knosys.2025.113573","url":null,"abstract":"<div><div>Metal defect semantic segmentation is a crucial process for classifying and locating defects during the industrial production process, which holds paramount importance in elevating the quality of metal products. Recently, deep learning has exhibited impressive capabilities in identifying and segmenting defects on metal surfaces. However, the prevalent use of fully supervised segmentation techniques demands a substantial amount of annotated data for effective model training, which is hard to obtain in real scenarios. Additionally, most defects of metal products exhibit indistinct edge details, which hinders precise defect localization. In this study, a Crop-Paste and diffusion-based semi-supervised segmentation network (CPDNet) is proposed to identify pixel-level defects on metal surfaces by utilizing data that are both labeled and unlabeled. Firstly, a semi-supervised training method Crop-Paste is proposed to facilitate the learning of comprehensive semantic features from an extensive of unlabeled images and a restricted set of labeled images. Secondly, a frequency-directed diffusion model is proposed to recover high frequency features of defects to generate more accurate segmentation results. Lastly, an edge aware module is proposed in Sobel mean-teacher (M-T) UNet to improve the boundary information representation associated with defects. The experimental results on four datasets related to metal surface defects and a multimodal dataset show that CPDNet achieves a better performance in comparison with those state-of-the-art methods.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113573"},"PeriodicalIF":7.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870738","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

FishDetectLLM: Multimodal instruction tuning with large language models for fish detection FishDetectLLM: 利用大型语言模型进行鱼类检测的多模式指令调整

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-14 DOI: 10.1016/j.knosys.2025.113418

Jiaxin Zhu , Shibai Yin , Xin Liu , Xingyang Wang , Yee-Hong Yang

{"title":"FishDetectLLM: Multimodal instruction tuning with large language models for fish detection","authors":"Jiaxin Zhu , Shibai Yin , Xin Liu , Xingyang Wang , Yee-Hong Yang","doi":"10.1016/j.knosys.2025.113418","DOIUrl":"10.1016/j.knosys.2025.113418","url":null,"abstract":"<div><div>Aquatic species play crucial roles in global ecosystems but are increasingly threatened by factors such as overfishing, coastal development and climate change. Existing deep learning methods address these challenges by employing powerful networks and large-scale, diverse datasets, separately tackling species recognition and trait identification during ongoing monitoring. However, they often exhibit limited generalization ability. Inspired by the human ability to quickly identify fish species and their locations with just a glance at an underwater image or scene, we introduce FishDetectLLM—a framework built on the lightweight TinyLLaVA architecture. FishDetectLLM utilizes the powerful reasoning capabilities and vast world knowledge of large language models (LLMs) to address the fish detection problem, providing both fish classification results and predicted bounding boxes for fish. Specifically, we create instruction dialogues for fish detection that connect fish taxonomy with classification descriptions and map location descriptions to the corresponding coordinates of bounding box in the input images from the recently released large-scale FishNet dataset. Then, we pretrain and fine-tune FishDetectLLM to achieve fish detection using the created dataset, leveraging the principle of augmenting human knowledge. Our results show that FishDetectLLM significantly outperforms existing multimodal LLMs and task-specific methods. Unlike conventional detection architectures that struggle to generalize beyond the training data, FishDetectLLM exhibits strong generalization capabilities, achieving robust performance on unseen data. This innovation paves the way for future applications of MLLMs in full research and offers valuable tools for the conservation of fish biodiversity.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113418"},"PeriodicalIF":7.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847437","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

D2AP: Double Debiasing with Adaptive Proxies for Domain Generalization in Noisy Environment 基于自适应代理的双去偏噪声环境下的领域泛化

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-14 DOI: 10.1016/j.knosys.2025.113458

Yunyun Wang, Xiaodong Liu, Yi Guo

{"title":"D2AP: Double Debiasing with Adaptive Proxies for Domain Generalization in Noisy Environment","authors":"Yunyun Wang, Xiaodong Liu, Yi Guo","doi":"10.1016/j.knosys.2025.113458","DOIUrl":"10.1016/j.knosys.2025.113458","url":null,"abstract":"<div><div>Domain Generalization (DG) methods commonly rely on multiple source domains with correct annotations, while it is usually difficult to obtain a large amount of clean source samples in practice, which greatly limits their application in real noisy environments. Hence, we consider a more realistic setting of Noisy Domain Generalization (NDG), which learns with noisy data from multiple source domains. A simple solution is to introduce previous noise learning strategies into individual domains to detect and correct the noisy samples independently. However, knowledge from other domains can also help the noise detection and correction for the current domain. Moreover, there will be domain bias of domain imbalance in clean samples after noise detection, and confirmation bias of inaccurate pseudo-labels in noisy samples after noise correction, which greatly affect the learning performance. To this end, we propose a novel Double Debiasing method with Adaptive Proxies (D2AP) for NDG learning. In D2AP, an adaptive sample disentangling module is first developed with multi-scale Gaussian Mixture Model, so as to enable a mutual noise disentangling across domains. Further, double debiasing is proposed with the assistance of adaptive proxies, in order to make domain-invariant prototypes less sensitive to domain imbalance, and calibrate the pseudo-labels for noisy data, so as to address the both biases. Finally, empirical results over three benchmark datasets demonstrate the effectiveness of our D2AP.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113458"},"PeriodicalIF":7.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835325","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

Boundary-aware Prototype Augmentation and Dual-level Knowledge Distillation for Non-Exemplar Class-Incremental Hashing 非样例类增量哈希的边界感知原型增强和双层知识蒸馏

IF 7.2 1区计算机科学

Knowledge-Based Systems Pub Date : 2025-04-14 DOI: 10.1016/j.knosys.2025.113520

Qinghang Su , Dayan Wu , Bo Li

{"title":"Boundary-aware Prototype Augmentation and Dual-level Knowledge Distillation for Non-Exemplar Class-Incremental Hashing","authors":"Qinghang Su , Dayan Wu , Bo Li","doi":"10.1016/j.knosys.2025.113520","DOIUrl":"10.1016/j.knosys.2025.113520","url":null,"abstract":"<div><div>Deep hashing methods are extensively applied in image retrieval for their efficiency and low storage demands. Recently, deep incremental hashing methods have addressed the challenge of adapting to new classes in non-stationary environments, while ensuring compatibility with existing classes. However, most of these methods require old-class samples for joint training to resist catastrophic forgetting, which is not always feasible due to privacy concerns. This constraint underscores the need for Non-Exemplar Class-Incremental Hashing (NECIH) approaches, designed to retain knowledge without storing old-class samples. In NECIH methodologies, hash prototypes are commonly employed to maintain the discriminability of hash codes. However, these prototypes often fail to represent old-class distribution accurately, causing confusion between old and new classes. Furthermore, traditional instance-level knowledge distillation techniques are insufficient for efficiently transferring the structural information inherent in the feature space. To tackle these challenges, we introduce a novel deep incremental hashing approach called Boundary-aware <strong>P</strong>rototype <strong>A</strong>ugmentation and Dual-level Knowledge <strong>D</strong>istillation for NEC<strong>IH</strong> (PADIH). PADIH comprises three key components: the Prototype-based Code Learning (PCL) module, the Boundary-aware Prototype Augmentation (BPA) module, and the Dual-level Knowledge Distillation (DKD) module. Specifically, the PCL module learns discriminative hash codes for new classes, while the BPA module augments the old-class prototypes into pseudo codes, with an emphasis on the distribution boundaries. Moreover, the DKD module integrates both instance-level and relation-level knowledge distillation to facilitate the transfer of comprehensive information between models. Extensive experiments conducted on four benchmarks across twelve incremental learning situations demonstrate the superior performance of PADIH.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113520"},"PeriodicalIF":7.2,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843955","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