检索结果-内蒙古大学图书馆

Two-Stage Guided Constraint Differential Evolution Algorithm

学校读者我要写书评

暂无评论

Journal of Network Intelligence

Journal of Network Intelligence 2023年第4期8卷 1109-1133页

作者： Sung, Tien-Wen Liang, Qiaoxin Hong, Chuanbo Huang, Zeming Li, Wei Nguyen, Trinh-Dong College of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China School of Electronic Electrical Engineering and Physics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China Department of Software Engineering University of Information Technology Ho Chi Minh City Viet Nam

The development of population intelligence has shown a great trend of a linear surge in recent years, and a large number of intelligent algorithms inspired by biology have been studied. Among them, differential evolution (DE) algorithms have attracted the attention of many researchers because of their simplicity, high efficiency, powerful search capability, etc. DE has strong exploitability and can approach the global optimum faster, but it cannot avoid the phenomenon of search stagnation and premature convergence. To address the drawbacks of DE, the two-stage bootstrap constrained differential evolution algorithm (TSGCDE) is proposed in this paper. In TSGCDE, instead of the traditional one population, the population is divided into two as a way to increase the diversity of the population. Divided into two stages, each stage searches for optimal solutions in different directions in different populations, and the optimal solutions and the bootstrap solutions generated by the populations in the two stages are bounded by each other’s bootstrap, which makes the DE have a more powerful optimal-seeking ability and easier to jump out of the local optimum. To validate the performance of TSGCDE, we conducted experiments on CEC2013 and CEC2014 benchmarks with some well-known algorithm variants, and the experimental results show that our proposed algorithm is competitive. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Swarm intelligence

AFF-Dehazing: Attention-based feature fusion network for low-light image Dehazing

学校读者我要写书评

暂无评论

AFF-Dehazing: Attention-based feature fusion network for low...

作者： Zhou, Yu Chen, Zhihua Sheng, Bin Li, Ping Kim, Jinman Wu, Enhua Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong School of Information Technologies The University of Sydney Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Faculty of Science and Technology University of Macau China

Images captured in haze conditions, especially at nighttime with low light, often suffer from degraded visibility, contrasts, and vividness, which makes it difficult to carry out the following vision tasks. In this article, we propose an attention-based feature fusion network (AFF-Dehazing) for low-light image dehazing. Our method decomposes the low-light image dehazing into two task-independent streams containing four modules: image dehazing module, low-light feature extractor module, feature fusion module, and image restoration module. The basic block of these modules is the proposed attention-based residual dense block. Since the dual-branch are used, AFF-Dehazing can avoid learning the mixed degradation all-in-one and enhance the details of low-light haze images. Extensive experiments show that our method surpasses previous state-of-the-art image dehazing methods and low-light enhancement methods by a very large margin both quantitatively and qualitatively. © 2021 John Wiley & Sons, Ltd.

关键词： Image reconstruction

state-based episodic memory for multi-agent reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Xiao Li, Wu-Jun Department of Computer Science and Technology Nanjing University National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University

Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the sample inefficiency problem. In this paper, we propose a simple yet effective approach, called state-based episodic memory (SEM), to improve sample efficiency in MARL. SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL. To the best of our knowledge, SEM is the first work to introduce EM into MARL. We can theoretically prove that, when using for MARL, SEM has lower space complexity and time complexity than state and action based EM (SAEM), which is originally proposed for single-agent reinforcement learning. Experimental results on StarCraft multi-agent challenge (SMAC) show that introducing episodic memory into MARL can improve sample efficiency and SEM can reduce storage cost and time cost compared with SAEM. Copyright © 2021, The Authors. All rights reserved.

关键词： Efficiency

Toward a Unified Framework for Unsupervised Complex Tabular Reasoning

学校读者我要写书评

暂无评论

Toward a Unified Framework for Unsupervised Complex Tabular ...

International Conference on Data Engineering

作者： Zhenyu Li Xiuxing Li Zhichao Duan Bowen Dong Ning Liu Jianyong Wang Department of Computer Science and Technology Tsinghua University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences School of Software Shandong University Jinan China

Structured tabular data exist across nearly all fields. Reasoning task over these data aims to answer questions or determine the truthiness of hypothesis sentences by understanding the semantic meaning of a table. While previous works have devoted significant efforts to the tabular reasoning task, they always assume there are sufficient labeled data. However, constructing reasoning samples over tables (and related text) is labor-intensive, especially when the reasoning process is complex. When labeled data is insufficient, the performance of models will suffer an unendurable decline. In this paper, we propose a unified framework for unsupervised complex tabular reasoning (UCTR), which generates sufficient and diverse synthetic data with complex logic for tabular reasoning tasks, assuming no human-annotated data at all. Specifically, we first utilize a random sampling strategy to collect diverse programs of different types and execute them on tables based on a "Program-Executor" module. To bridge the gap between the programs and natural language sentences, we design a powerful "NL-Generator" module to generate natural language sentences with complex logic from these programs. Since a table often occurs with its surrounding texts, we further propose novel "Table-to-Text" and "Text-to-Table" operators to handle joint table-text reasoning scenarios. This way, we can adequately exploit the unlabeled table resources to obtain a well-performed reasoning model under an unsupervised setting. Our experiments cover different tasks (question answering and fact verification) and different domains (general and specific), showing that our unsupervised methods can achieve at most 93% performance compared to supervised models. The impressive performance demonstrates that UCTR can significantly reduce the dependence on manual annotation. Moreover, we also find that it can substantially boost the supervised performance in low-resourced domains as a data augmentation technique.

关键词：

Self-adaptive vision-language model for 3D segmentation of pulmonary artery and vein

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Guo, Xiaotong Yang, Deqian Wang, Dan Zhao, Haochen Li, Yuan Sui, Zhilin Zhou, Tao Zhang, Lijun Meng, Yanda State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Department of Thoracic Surgery National Clinical Research Center for Cancer Cancer Hospital Shenzhen Hospital China School of Intelligent Science and Technology Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China R&D Center Guangxi Huayi Artificial Intelligence Medical Technology Co. Ltd. China School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Exeter Exeter United Kingdom Department of Cardiovascular & Metabolic Medicine University of Liverpool Liverpool United Kingdom Guangzhou Jiayi Software Technology Co. Ltd. China

Accurate segmentation of pulmonary structures is crucial in clinical diagnosis, disease study, and treatment planning. Significant progress has been made in deep learning-based segmentation techniques, but most require much labeled data for training. Consequently, developing precise segmentation methods that demand fewer labeled datasets is paramount in medical image analysis. The emergence of pre-trained vision-language foundation models, such as CLIP, recently opened the door for universal computer vision tasks. Exploiting the generalization ability of these pre-trained foundation models on downstream tasks, such as segmentation, leads to unexpected performance with a relatively small amount of labeled data. However, exploring these models for pulmonary artery-vein segmentation is still limited. This paper proposes a novel framework called Language-guided self-adaptive Cross-Attention Fusion Framework. Our method adopts pre-trained CLIP as a strong feature extractor for generating the segmentation of 3D CT scans, while adaptively aggregating the cross-modality of text and image representations. We propose a s pecially designed adapter module to fine-tune pre-trained CLIP with a self-adaptive learning strategy to effectively fuse the two modalities of embeddings. We extensively validate our method on a local dataset, which is the largest pulmonary artery-vein CT dataset to date and consists of 718 labeled data in total. The experiments show that our method outperformed other state-of-the-art methods by a large margin. Our data and code will be made publicly available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

学校读者我要写书评

暂无评论

Robust Generalization Against Photon-Limited Corruptions via...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhuo Huang Miaoxi Zhu Xiaobo Xia Li Shen Jun Yu Chen Gong Bo Han Bo Du Tongliang Liu Sydney AI Centre The University of Sydney National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University JD Explore Academy Department of Automation University of Science and Technology of China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Department of Computer Science Hong Kong Baptist University

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.

关键词：

An empirical study on the impact of class overlap in just-in-time software defect prediction 33

学校读者我要写书评

暂无评论

An empirical study on the impact of class overlap in just-in...

33rd International Conference on software Engineering and Knowledge Engineering, SEKE 2021

作者： Yi, Minyang Fan, Guisheng Yu, Huiqun Yang, Xingguang Department of Computer Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China Shanghai Engineering Research Center of Smart Energy Shanghai China

ISBN: (纸本)1891706527

Just-in-time software defect prediction (JIT-SDP) is an active research topic in the field of software engineering, aiming at identifying defect-inducing code changes. Most of the current JIT-SDP work focused on model construction. It is often ignored that the performance of classifiers often depends on high quality data. In this paper, we first investigate the impact of the class overlap problem on the performance of the classifiers in JIT-SDP, and propose a new effective preprocessing method (IKMCCA-TL) combining improved K-Means clustering cleaning approach and Tomek-link method. In order to objectively estimate the impact of class overlap on the classifiers in JIT-SDP, we conduct a large-scale empirical study on the data sets of six open source projects and compare the performance of LR, RF and KNN classifiers by using IKMCCA or KMCCA or NCL and without cleaning data. Experimental results show that after removing overlapping instances, the performance of the classifiers is significantly improved in terms of balance, recall and AUC and our proposed method achieves the best performance. © 2021 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： K-means clustering

Practitioners’ Expectations on Log Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xiaoxue Li, Yishu Keung, Jacky Yu, Xiao Zou, Huiqi Yang, Zhen Sarro, Federica Barr, Earl T. Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University Hong Kong Department of Computer Science City University of Hong Kong Hong Kong State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Department of Computer Science Johns Hopkins University Baltimore United States School of Computer Science and Technology Shandong University Shandong China Department of Computer Science University College London London United Kingdom

Log anomaly detection has become a common practice for software engineers to analyze software system behavior. Despite significant research efforts in log anomaly detection over the past decade, it remains unclear what are practitioners’ expectations on log anomaly detection and whether current research meets their needs. To fill this gap, we conduct an empirical study, surveying 312 practitioners from 36 countries about their expectations on log anomaly detection. In particular, we investigate various factors influencing practitioners’ willingness to adopt log anomaly detection tools. We then perform a literature review on log anomaly detection, focusing on publications in premier venues from 2014 to 2024, to compare practitioners’ needs with the current state of research. Based on this comparison, we highlight the directions for researchers to focus on to develop log anomaly detection techniques that better meet practitioners’ expectations. © 2024, CC BY-NC-SA.

关键词：

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning