Few-shot anomaly detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pretrained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal interference. To bridge these gaps, this study proposes VTFusion, a vision-text multimodal fusion framework tailored for FSAD. The framework rests on two core designs. First, adaptive feature extractors for both image and text modalities are introduced to learn task-specific representations, bridging the domain gap between pretrained models and industrial data; this is further augmented by generating diverse synthetic anomalies to enhance feature discriminability. Second, a dedicated multimodal prediction fusion module is developed, comprising a fusion block that facilitates rich cross-modal information exchange and a segmentation network that generates refined pixel-level anomaly maps under multimodal guidance. VTFusion significantly advances FSAD performance, achieving image-level area under the receiver operating characteristics (AUROCs) of 96.8% and 86.2% in the 2-shot scenario on the MVTec AD and VisA datasets, respectively. Furthermore, VTFusion achieves an AUPRO of 93.5% on a real-world dataset of industrial automotive plastic parts introduced in this article, further demonstrating its practical applicability in demanding industrial scenarios.
{"title":"VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detection.","authors":"Yuxin Jiang,Yunkang Cao,Yuqi Cheng,Yiheng Zhang,Weiming Shen","doi":"10.1109/tcyb.2026.3651630","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651630","url":null,"abstract":"Few-shot anomaly detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pretrained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal interference. To bridge these gaps, this study proposes VTFusion, a vision-text multimodal fusion framework tailored for FSAD. The framework rests on two core designs. First, adaptive feature extractors for both image and text modalities are introduced to learn task-specific representations, bridging the domain gap between pretrained models and industrial data; this is further augmented by generating diverse synthetic anomalies to enhance feature discriminability. Second, a dedicated multimodal prediction fusion module is developed, comprising a fusion block that facilitates rich cross-modal information exchange and a segmentation network that generates refined pixel-level anomaly maps under multimodal guidance. VTFusion significantly advances FSAD performance, achieving image-level area under the receiver operating characteristics (AUROCs) of 96.8% and 86.2% in the 2-shot scenario on the MVTec AD and VisA datasets, respectively. Furthermore, VTFusion achieves an AUPRO of 93.5% on a real-world dataset of industrial automotive plastic parts introduced in this article, further demonstrating its practical applicability in demanding industrial scenarios.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"263 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146015297","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}
A low-pass filter is essential for stabilizing strictly proper repetitive-control systems, but it inevitably degrades steady-state tracking accuracy due to gain attenuation and phase lag. This article presents a new filter design and optimization method that improves both transient response and steady-state accuracy in continuous-time repetitive-control systems. First, the gain and phase characteristics of conventional filter-based repetitive controllers are rigorously analyzed to reveal the relationship between filter parameters and tracking performance. Based on this analysis, a new filter structure is designed to precisely compensate for gain attenuation and phase delay, specifically at the fundamental frequency, by minimizing the error term without increasing the filter bandwidth. A guideline for selecting the filter parameters for varying periodic trajectories is also provided. In addition, according to the one-to-one mapping between control and learning behaviors and their respective gains, dual performance indices are constructed to account for tracking error and control effort across multiple learning cycles. A multiobjective optimization framework is then developed to directly tune these gains subject to stability constraints, achieving an optimal balance between rapid transient convergence and control energy efficiency. Experimental results validate the effectiveness and superiority of the design.
{"title":"A New Filter Design and Optimization Framework for Enhancing Transient and Steady-State Tracking in Repetitive-Control Systems.","authors":"Manli Zhang,Chengda Lu,Yibing Wang,Shengnan Tian,Min Wu,Makoto Iwasaki","doi":"10.1109/tcyb.2026.3651712","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651712","url":null,"abstract":"A low-pass filter is essential for stabilizing strictly proper repetitive-control systems, but it inevitably degrades steady-state tracking accuracy due to gain attenuation and phase lag. This article presents a new filter design and optimization method that improves both transient response and steady-state accuracy in continuous-time repetitive-control systems. First, the gain and phase characteristics of conventional filter-based repetitive controllers are rigorously analyzed to reveal the relationship between filter parameters and tracking performance. Based on this analysis, a new filter structure is designed to precisely compensate for gain attenuation and phase delay, specifically at the fundamental frequency, by minimizing the error term without increasing the filter bandwidth. A guideline for selecting the filter parameters for varying periodic trajectories is also provided. In addition, according to the one-to-one mapping between control and learning behaviors and their respective gains, dual performance indices are constructed to account for tracking error and control effort across multiple learning cycles. A multiobjective optimization framework is then developed to directly tune these gains subject to stability constraints, achieving an optimal balance between rapid transient convergence and control energy efficiency. Experimental results validate the effectiveness and superiority of the design.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"35 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146015433","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}
Pub Date : 2026-01-21DOI: 10.1109/tcyb.2026.3651581
Xiaoxiao Wang,Zhiyong Bao,Xiaomiao Li,Hak-Keung Lam,Ziwei Wang
The co-design problem of dual event-triggered (DET) mechanism and polynomial dynamic output-feedback (PDOF) controller is investigated for positive polynomial fuzzy systems (PPFSs) with uncertainty and disturbance constraints. Specifically, a 1-norm DET mechanism compatible with the positivity of PPFSs is proposed to asynchronously update measurement outputs and PDOF control signals. However, synthesizing this DET-PDOF controller proves challenging due to the coupling of multiple unknown PDOF controller gain matrices within the positivity and stability conditions, which results in complex nonconvex terms. By introducing auxiliary variables and constraints, sufficient conditions for DET-PDOF controller solution are given to ensure both the $L_{1}$ -gain performance and strict positivity of PPFSs with uncertainty and disturbance. Moreover, existing stability analysis results that ignore membership functions (MFs) tend to be conservative, implying that the obtained DET-PDOF controller is effective only within a limited triggered threshold range, leading to worse transmission performance. Therefore, a multivariate optimization method based on an improved genetic algorithm (IGA), which accounts for the system states and PDOF controller variables, is developed to substantially expand the admissible DET threshold range while effectively suppressing dual-triggering frequencies. Finally, a numerical example and a two-linked tank system with parameter uncertainty are provided to validate the feasibility of the proposed scheme.
{"title":"Dual Event-Triggered Polynomial Dynamic Output Control for Positive Fuzzy Systems via an IT2 Membership Function Relaxation Method.","authors":"Xiaoxiao Wang,Zhiyong Bao,Xiaomiao Li,Hak-Keung Lam,Ziwei Wang","doi":"10.1109/tcyb.2026.3651581","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651581","url":null,"abstract":"The co-design problem of dual event-triggered (DET) mechanism and polynomial dynamic output-feedback (PDOF) controller is investigated for positive polynomial fuzzy systems (PPFSs) with uncertainty and disturbance constraints. Specifically, a 1-norm DET mechanism compatible with the positivity of PPFSs is proposed to asynchronously update measurement outputs and PDOF control signals. However, synthesizing this DET-PDOF controller proves challenging due to the coupling of multiple unknown PDOF controller gain matrices within the positivity and stability conditions, which results in complex nonconvex terms. By introducing auxiliary variables and constraints, sufficient conditions for DET-PDOF controller solution are given to ensure both the $L_{1}$ -gain performance and strict positivity of PPFSs with uncertainty and disturbance. Moreover, existing stability analysis results that ignore membership functions (MFs) tend to be conservative, implying that the obtained DET-PDOF controller is effective only within a limited triggered threshold range, leading to worse transmission performance. Therefore, a multivariate optimization method based on an improved genetic algorithm (IGA), which accounts for the system states and PDOF controller variables, is developed to substantially expand the admissible DET threshold range while effectively suppressing dual-triggering frequencies. Finally, a numerical example and a two-linked tank system with parameter uncertainty are provided to validate the feasibility of the proposed scheme.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"29 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146015300","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}
Pub Date : 2026-01-19DOI: 10.1109/tcyb.2026.3651462
Weihao Pan, Xianfu Zhang, Lu Liu, Zhiyu Duan
{"title":"Decentralized Impulsive Control for Nonlinear Interconnected Systems Based on Dynamic Event-Triggered Mechanism","authors":"Weihao Pan, Xianfu Zhang, Lu Liu, Zhiyu Duan","doi":"10.1109/tcyb.2026.3651462","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651462","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"27 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001267","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}
Pub Date : 2026-01-16DOI: 10.1109/TCYB.2025.3650459
Lei Hao, Lina Xu, Chang Liu, Yanni Dong
Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet). The LASFNet adopts a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. The attention-guided self-modulation feature fusion (ASFF) module in the model adaptively adjusts the responses of fused features at both global and local levels, promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that our approach achieves a favorable efficiency-accuracy tradeoff. Compared to state-of-the-art methods, LASFNet reduced the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy mean average precision (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet.
{"title":"LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection.","authors":"Lei Hao, Lina Xu, Chang Liu, Yanni Dong","doi":"10.1109/TCYB.2025.3650459","DOIUrl":"https://doi.org/10.1109/TCYB.2025.3650459","url":null,"abstract":"<p><p>Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet). The LASFNet adopts a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. The attention-guided self-modulation feature fusion (ASFF) module in the model adaptively adjusts the responses of fused features at both global and local levels, promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that our approach achieves a favorable efficiency-accuracy tradeoff. Compared to state-of-the-art methods, LASFNet reduced the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy mean average precision (mAP) by 1%-3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet.</p>","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":10.5,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145989039","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：