Information Sciences最新文献_第7页

Synchronization of quaternion-valued multi-layer coupled networks: An adaptive activation-time-based event-triggered scheme

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-20 DOI: 10.1016/j.ins.2025.121999

Yue Ren , Haijun Jiang , Cheng Hu , Lianyang Hu , Jiarong Li

引用次数: 0

The grouping weighted averaging operator via three-way conflict analysis

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121990

Xiaonan Li , Rong Liang , Huangjian Yi

引用次数: 0

Preserving knowledge from the source domain for cross-domain person re-identification

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121994

Yifeng Gou , Ziqiang Li , Junyin Zhang , Yongxin Ge

{"title":"Preserving knowledge from the source domain for cross-domain person re-identification","authors":"Yifeng Gou , Ziqiang Li , Junyin Zhang , Yongxin Ge","doi":"10.1016/j.ins.2025.121994","DOIUrl":"10.1016/j.ins.2025.121994","url":null,"abstract":"<div><div>Although recent cross-domain person re-identification approaches have obtained great progress, they still suffer from two core issues. The first one is the insufficient useful knowledge transfer, which means the beneficial knowledge learned from the source domain is not utilized fully due to the fine-tuning process of the two-stage training especially. The second problem is the inappropriate transfer of the source domain knowledge. Concretely, this knowledge is not distinguished before being transferred, leading to the domain-specific knowledge is detrimental to the target domain performance. To circumvent them, we design a novel collaborative learning method named Preserving Knowledge from the Source Domain (PKSD) from both instance and pixel levels, composed of Ranking-guided Instance Selection (RIS) and Projection based Gradient Selection (PGS). Firstly, the collaborative learning manner could safeguard sufficient knowledge transfer from the source domain. Additionally, RIS tries to select reliable and informative samples from the source domain dataset for training to provide sufficient domain-shared knowledge at the instance level. Subsequently, PGS fine-tunes the feature maps of the selected samples according to the gradient modifying at the pixel level of feature maps to suppress remaining domain-specific knowledge from the source domain. Experiments show that PKSD outperforms existing state-of-the-art methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121994"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454854","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 discriminant projection with cosine weighted dynamic graph regularization for feature extraction

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121987

Weijia Tang , Hongmei Chen , Tengyu Yin , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li

{"title":"Joint discriminant projection with cosine weighted dynamic graph regularization for feature extraction","authors":"Weijia Tang , Hongmei Chen , Tengyu Yin , Zhong Yuan , Chuan Luo , Shi-Jinn Horng , Tianrui Li","doi":"10.1016/j.ins.2025.121987","DOIUrl":"10.1016/j.ins.2025.121987","url":null,"abstract":"<div><div>Obtaining low-dimensional discriminative features for original-dimensional data through projection in machine learning is challenging. The problems facing discriminative projection are: The data contains noise and outliers, and the effectiveness of the projection will be negatively affected. Extracting discriminative features by combining linear discriminative projection with preserving the local geometric structure is complex. The excess edges in the graph regularity term introduce redundant information, negatively impacting discriminative feature extraction. To address the issues above, the Joint Discriminant Projection with Cosine-Weighted Dynamic Graph Regularization (JDPCDG) is devised for feature extraction. The JDPCDG model consists of three main contributions: (1) The <span><math><msub><mrow><mi>ξ</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>-norm and <span><math><msub><mrow><mi>ξ</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span>-norm are designed to adapt to outlier samples and noise features, respectively. (2) The <span><math><msub><mrow><mi>S</mi></mrow><mrow><mi>c</mi><mi>o</mi><mi>s</mi></mrow></msub></math></span> similarity graph matrix constructed with cosine weights is designed to preserve the global structure information within the class and obtain the local structure information in combination with the LDA model. (3) A framework model is constructed by effectively integrating manifold learning, linear discriminant analysis, and reconstructed data. Comprehensive experiments on synthetic data and multiple real-world datasets consistently demonstrate their superior performance over other relevant feature extraction methods. Experiments are conducted on non-image and image data, comparing them with related methods. The experimental results verify the robustness and superiority of the proposed JDPCDG.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121987"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454855","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

Out-of-distribution detection with non-semantic exploration

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121989

Zhen Fang, Jie Lu, Guangquan Zhang

{"title":"Out-of-distribution detection with non-semantic exploration","authors":"Zhen Fang, Jie Lu, Guangquan Zhang","doi":"10.1016/j.ins.2025.121989","DOIUrl":"10.1016/j.ins.2025.121989","url":null,"abstract":"<div><div>Out-of-distribution (OOD) detection is crucial in modern deep learning applications, as it can identify OOD data drawn from distributions differing from those of the in-distribution (ID) data. Advanced OOD detection methods primarily rely on post-hoc strategies, which identify OOD data by analyzing the predictions of a model well-trained on ID data. However, deep models are known to be impacted by spurious features such as backgrounds, causing existing OOD detection methods to fail in identifying OOD data that share the same spurious features as ID data. Therefore, this paper studies how to mitigate spurious features to improve OOD detection. To address this challenge, we propose a novel method called <u>N</u>on-<u>s</u>emantic <u>E</u>xploration OOD <u>D</u>etection (NsED), which focuses on exploring and exploiting non-semantic features. In particular, NsED first explores non-semantic features in an OOD generalization manner. These non-semantic features are then used to train deep models to be more robust against spurious features. Through extensive experiments on representative benchmarks, we show that NsED significantly and consistently improves the detection performance of many representative post-hoc OOD detection methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121989"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454856","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

Unlocking the power of knowledge for few-shot fault diagnosis: A review from a knowledge perspective

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121996

Pei Lai , Fan Zhang , Tianrui Li , Jin Guo , Fei Teng

{"title":"Unlocking the power of knowledge for few-shot fault diagnosis: A review from a knowledge perspective","authors":"Pei Lai , Fan Zhang , Tianrui Li , Jin Guo , Fei Teng","doi":"10.1016/j.ins.2025.121996","DOIUrl":"10.1016/j.ins.2025.121996","url":null,"abstract":"<div><div>Fault diagnosis has long been a topic of great interest, owing to a disaster that can result from the faults of safety-critical systems. In recent years, researchers have realized that fault diagnosis of real equipment, and more precisely the fault identification task, is not simply a pattern recognition problem but instead, a few-shot classification problem. Despite valuable publications on few-shot fault diagnosis (FSFD), these surveys have primarily focused on a methodological perspective. Furthermore, few articles have been published to provide a comprehensive summary of FSFD methods from a knowledge perspective. This paper proposes a comprehensive taxonomy for FSFD methods that classifies them into data-based and knowledge-based approaches, as knowledge and data represent different levels in the knowledge perspective. The paper focuses on the knowledge-based approaches, which include knowledge embedding and knowledge discovery. These approaches aim to leverage the knowledge available in limited datasets and auxiliary datasets. The paper examines various knowledge representations such as predefined rules, learning biases, network parameters, and feature representations. Furthermore, the study assesses potential challenges and future research directions from a knowledge perspective. Finally, some public datasets and code repositories are summarized. This paper can serve as a useful reference for advancing FSFD research.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121996"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473967","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

Sparse personalized federated class-incremental learning

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121992

Youchao Liu, Dingjiang Huang

{"title":"Sparse personalized federated class-incremental learning","authors":"Youchao Liu, Dingjiang Huang","doi":"10.1016/j.ins.2025.121992","DOIUrl":"10.1016/j.ins.2025.121992","url":null,"abstract":"<div><div>Recently federated learning (FL) has attracted growing attention by performing data-private collaborative training on decentralized clients. However, the majority of existing FL methods concentrate on single-task scenarios with static data. In real-world scenarios, local clients usually continuously collect new classes from the data stream and have just a small amount of memory to store training samples of old classes. Using single-task models directly will lead to significant catastrophic forgetting in old classes. In addition, there are some typical challenges in FL scenarios, such as computation and communication overhead, data heterogeneity, etc. To comprehensively describe these challenges, we propose a new Personalized Federated Class-Incremental Learning (PFCIL) problem. Furthermore, we propose an innovative Sparse Personalized Federated Class-Incremental Learning (SpaPFCIL) framework that learns a personalized class-incremental model for each client through sparse training to solve this problem. Unlike most knowledge distillation-based methods, our framework does not require additional data to assist. Specifically, to tackle catastrophic forgetting brought by class-incremental tasks, we utilize expandable class-incremental models instead of single-task models. For typical challenges in FL, we use dynamic sparse training to customize sparse local models on clients. It alleviates the negative effects of data heterogeneity and over-parameterization. Our framework outperforms state-of-the-art methods in terms of average accuracy on representative benchmark datasets by 3.3% to 43.6%.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121992"},"PeriodicalIF":8.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454153","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

Cluster output synchronization analysis of coupled fractional-order uncertain neural networks

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-19 DOI: 10.1016/j.ins.2025.121993

Junhong Zhao , Yunliu Li , Ting Liu , Peng Liu , Junwei Sun

引用次数: 0

Self-supervised temporal adaptive learning for weakly-supervised temporal action localization

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-18 DOI: 10.1016/j.ins.2025.121986

Jinrong Sheng, Jiaruo Yu, Ziqiang Li, Ao Li, Yongxin Ge

{"title":"Self-supervised temporal adaptive learning for weakly-supervised temporal action localization","authors":"Jinrong Sheng, Jiaruo Yu, Ziqiang Li, Ao Li, Yongxin Ge","doi":"10.1016/j.ins.2025.121986","DOIUrl":"10.1016/j.ins.2025.121986","url":null,"abstract":"<div><div>Weakly-supervised temporal action localization (WTAL) identifies and localizes actions in untrimmed videos with only video-level labels. Most methods prioritize discriminative snippets, often neglecting of hard action snippets while focusing on class-specific background. Although recent methods have tackled this issue through temporal modeling, they overlook the local temporal structure of actions. To model such temporal structure effectively, we propose a novel self-supervised temporal adaptive learning (STAL) framework, which is composed of two core parts, i.e. self-supervised temporal learning (STL) network and the adaptive learning unit (ALU). Specifically, STL constructs a self-supervised task by performing an erasure and reconstruction process. This pseudo-label-based method relies on a classification task to perceive continuous temporal information for action localization task. To avoid the disturbance of un-confident pseudo labels during self-supervised learning process, two adaptive learning strategies of ALU are designed from two perspectives. In detail, a task-adaptive learning strategy is used to train the proposed tasks to the best for more reliable pseudo labels. Meanwhile, a score-adaptive learning strategy is designed to balance class activation and attention scores. Experiments on two classical datasets, namely, THUMOS14 and ActivityNet datasets, verify the effectiveness of our method.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"705 ","pages":"Article 121986"},"PeriodicalIF":8.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437279","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

Fractal spatio-temporal scale-free messaging: Amplitude modulation of self-executable carriers given by the Weierstrass function's components

IF 8.1 1区计算机科学

Information Sciences Pub Date : 2025-02-18 DOI: 10.1016/j.ins.2025.121988

Hector Zenil , Luan Carlos de Sena Monteiro Ozelim

{"title":"Fractal spatio-temporal scale-free messaging: Amplitude modulation of self-executable carriers given by the Weierstrass function's components","authors":"Hector Zenil , Luan Carlos de Sena Monteiro Ozelim","doi":"10.1016/j.ins.2025.121988","DOIUrl":"10.1016/j.ins.2025.121988","url":null,"abstract":"<div><div>In communication systems, the circumstances and capabilities of senders and receivers cannot be known/assumed beforehand so as to design optimal semantic transference strategies. Regardless of the recipient (plants, insects, or even life forms unknown on Earth), the spatio-temporal scale of a message could be inappropriate and may never be decoded due to incompatibilities at both ends. We devise a new method to encode messages that is agnostic vis-a-vis space and time scales. We propose the use of fractal functions as self-executable carriers for sending messages, given their properties of structural self-similarity and scale invariance. We call this ‘fractal messaging’. Starting from a spatial embedding, we introduce a framework for a space-time scale-free messaging approach. In creating a space and time agnostic framework for message transmission, encoding a message that could be decoded at several spatio-temporal scales is the objective. Our core idea is to encode a binary message as waves along infinitely many frequencies (in power-like distributions) and amplitudes, transmit such a message, and then decode and reproduce it. To do so, the components/cycles of the Weierstrass function, a known fractal, are used as carriers of the message. Each component will have its amplitude modulated to embed the binary stream, allowing for a space-time agnostic approach to messaging.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"706 ","pages":"Article 121988"},"PeriodicalIF":8.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0