检索结果-内蒙古大学图书馆

HSALC: hard sample aware label correction for medical image classification

Multimedia Tools and Applications 2024年 1-21页

作者： Wang, Yangtao Ye, Yicheng Xie, Yanzhao Tang, Maobin Fan, Lisheng Metaverse Research Institute School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

Medical image automatic classification has always been a research hotspot, but the existing methods suffer from the label noise problem, which either discards those samples with noisy labels or produces wrong label correction, seriously preventing the medical image classification performance improvement. To address the above problems, in this paper, we propose a hard sample aware label correction (termed as HSALC) method for medical image classification. Our HSALC mainly consists of a sample division module, a clean·hard·noisy (termed as CHN) detection module and a label noise correction module. First, in the sample division module, we design a sample division criterion based on the training difficulty and training losses to divide all samples into three preliminary subsets: clean samples, hard samples and noisy samples. Second, in the CHN detection module, we add noise to the above clean samples and repeatedly adopt the sample division criterion to effectively detect all data, which helps obtain highly reliable clean samples, hard samples and noisy samples. Finally, in the label noise correction module, in order to make full use of each available sample, we train a correction model to purify and correct the wrong labels of noisy samples as much as possible, which brings a highly purified dataset. We conduct extensive experiments on five image datasets including three medical image datasets and two natural image datasets. Experimental results demonstrate that HSALC can greatly promote classification performance on noisily labeled datasets, especially with high noise ratios. The source code of this paper is publicly available at GitHub: https://***/YYC117/HSALC. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Document-Level Event Factuality Identification via Reinforced Semantic Learning Network

引用

Journal of computer science & Technology 2024年第6期39卷 1248-1268页

作者： Zhong Qian Pei-Feng Li Qiao-Ming Zhu Guo-Dong Zhou School of Computer Science and Technology Soochow UniversitySuzhou 215006China AI Research Institute Soochow UniversitySuzhou 215006China

This paper focuses on document-level event factuality identification (DEFI), which predicts the factual nature of an event from the view of a document. As the document-level sub-task of event factuality identification (EFI), DEFI is a challenging and fundamental task in natural language processing (NLP). Currently, most existing studies focus on sentence-level event factuality identification (SEFI). However, DEFI is still in the early stage and related studies are quite limited. Previous work is heavily dependent on various NLP tools and annotated information, e.g., dependency trees, event triggers, speculative and negative cues, and does not consider filtering irrelevant and noisy texts that can lead to wrong results. To address these issues, this paper proposes a reinforced multi-granularity hierarchical network model: Reinforced Semantic Learning Network (RSLN), which means it can learn semantics from sentences and tokens at various levels of granularity and hierarchy. Since integrated with hierarchical reinforcement learning (HRL), the RSLN model is able to select relevant and meaningful sentences and tokens. Then, RSLN encodes the event and document according to these selected texts. To evaluate our model, based on the DLEF (Document-Level Event Factuality) corpus, we annotate the ExDLEF corpus as the benchmark dataset. Experimental results show that the RSLN model outperforms several state-of-the-arts.

关键词： document-level event factuality identification hierarchical reinforcement learning attention network multi-granularity encoding

来源：评论

学校读者我要写书评

暂无评论

Iterative Phase Noise Suppression for Full-Duplex Communication Systems

引用

China Communications 2023年第2期20卷 226-234页

作者： Pengxin Guan Yiru Wang Hongkang Yu Yuping Zhao School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Wireless Product Research and Development Institute ZTE CorporationShenzhen 518057China

Oscillator phase noise is one of the bottlenecks that limits the self-interference(SI)cancellation capability of full-duplex *** this paper,we propose a method for the suppression of common phase error(CPE)and intercarrier interference(ICI)induced by the phase noise in full-duplex orthogonal frequency division multiplexing(OFDM)***,we regard the effect of CPE as a portion of the SI channel and perform estimation,reconstruction and elimination in the time ***,the ICI signal is estimated and suppressed in the frequency ***,by analysing the performance of proposed algorithm,we further develop an iterative mechanism to reduce the parameter estimation error and improve SI cancellation *** results show that the proposed method has a significant SI cancellation capability improvement over the traditional SI cancellation schemes.

关键词： full-duplex self-interference phase noise suppression

来源：评论

学校读者我要写书评

暂无评论

TSCompiler: efficient compilation framework for dynamic-shape models

引用

science China(Information sciences) 2024年第10期67卷 67-84页

作者： Xiang LUO Chen ZHANG Chenbo GENG Yanzhi YI Jiahui HU Renwei ZHANG Zhen ZHANG Gianpietro CONSOLARO Fan YANG Tun LU Ning GU Li SHANG School of Computer Science Fudan University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University School of Computer Science and Technology Harbin Institute of Technology Huawei Technologies Co. Ltd. Huawei Paris Research Center School of Microelectronics Fudan University

Today's deep learning models face an increasing demand to handle dynamic shape tensors and computation whose shape information remains unknown at compile time and varies in a nearly infinite range at runtime. This shape dynamism brings tremendous challenges for existing compilation pipelines designed for static models which optimize tensor programs relying on exact shape values. This paper presents TSCompiler, an end-to-end compilation framework for dynamic shape models. TSCompiler first proposes a symbolic shape propagation algorithm to recover symbolic shape information at compile time to enable subsequent optimizations. TSCompiler then partitions the shape-annotated computation graph into multiple subgraphs and fine-tunes the backbone operators from the subgraph within a hardware-aligned search space to find a collection of high-performance schedules. TSCompiler can propagate the explored backbone schedule to other fusion groups within the same subgraph to generate a set of parameterized tensor programs for fused cases based on dependence analysis. At runtime, TSCompiler utilizes an occupancy-targeted cost model to select from pre-compiled tensor programs for varied tensor shapes. Extensive evaluations show that TSCompiler can achieve state-of-the-art speedups for dynamic shape models. For example, we can improve kernel efficiency by up to 3.97× on NVIDIA RTX3090, and 10.30× on NVIDIA A100 and achieve up to five orders of magnitude speedups on end-to-end latency.

关键词： machine learning tensor compilers dynamic shape operator fusion code generation auto-tuning

来源：评论

学校读者我要写书评

暂无评论

COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection

引用

science China(Information sciences) 2025年第1期68卷 189-203页

作者： Xiaoqin ZHANG Zhenni YU Li ZHAO Deng-Ping FAN Guobao XIAO Zhejiang Province Key Laboratory of Intelligent Informatics for Safety and Emergency Wenzhou University Nankai International Advanced Research Institute (SHENZHEN FUTIAN) College of Computer Science Nankai University School of Computer Science and Technology Tongji University

We rethink the segment anything model(SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection(COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework for COD. Our network aims to enhance the single prompt strategy in SAM to a multiprompt strategy. To achieve this, we propose an edge gradient extraction module, which generates a mask containing gradient information regarding the boundaries of camouflaged objects. This gradient mask is then used as a novel boundary prompt, enhancing the segmentation process. Thereafter, we design a box-boundary mutual guidance module, which fosters more precise and comprehensive feature extraction via mutual guidance between a boundary prompt and a box prompt. This collaboration enhances the model's ability to accurately detect camouflaged objects. Moreover, we employ the discrete wavelet transform to extract high-frequency features from image embeddings. The high-frequency features serve as a supplementary component to the multiprompt ***, our COMPrompter guides the network to achieve enhanced segmentation results, thereby advancing the development of SAM in terms of COD. Experimental results across COD benchmarks demonstrate that COMPrompter achieves a cutting-edge performance, surpassing the current leading model by an average positive metric of 2.2% in COD10K. In the specific application of COD, the experimental results in polyp segmentation show that our model is superior to top-tier methods as well. The code will be made available at https://***/guobaoxiao/COMPrompter.

关键词： segment anything model camouflaged object detection boundary prompt

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2253-2269页

作者： Kui Jiang Ruoxi Wang Yi Xiao Junjun Jiang Xin Xu Tao Lu IEEE the School of Computer Science and Technology Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology the School of Artificial Intelligence Jianghan University the School of Geodesy and Geomatics Wuhan University the Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology the School of Computer Science and Engineering and also with the Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology

Degradation under challenging conditions such as rain, haze, and low light not only diminishes content visibility, but also results in additional degradation side effects, including detail occlusion and color distortion. However, current technologies have barely explored the correlation between perturbation removal and background restoration, consequently struggling to generate high-naturalness content in challenging scenarios. In this paper, we rethink the image enhancement task from the perspective of joint optimization: Perturbation removal and texture reconstruction. To this end, we advise an efficient yet effective image enhancement model, termed the perturbation-guided texture reconstruction network(PerTeRNet). It contains two subnetworks designed for the perturbation elimination and texture reconstruction tasks, respectively. To facilitate texture recovery,we develop a novel perturbation-guided texture enhancement module(PerTEM) to connect these two tasks, where informative background features are extracted from the input with the guidance of predicted perturbation priors. To alleviate the learning burden and computational cost, we suggest performing perturbation removal in a sub-space and exploiting super-resolution to infer high-frequency background details. Our PerTeRNet has demonstrated significant superiority over typical methods in both quantitative and qualitative measures, as evidenced by extensive experimental results on popular image enhancement and joint detection tasks. The source code is available at https://***/kuijiang94/PerTeRNet.

关键词： Association learning attention mechanism image enhancement perturbation modeling

来源：评论

学校读者我要写书评

暂无评论

PathActMarker:an R package for inferring pathway activity of complex diseases

引用

Frontiers of computer science 2025年第3期19卷 123-124页

作者： Xingyi LI Jun HAO Zhelin ZHAO Junming LI Xingyu LIAO Min LI Xuequn SHANG School of Computer Science Northwestern Polytechnical UniversityXi’an 710072China Research&Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518063China School of Software Northwestern Polytechnical UniversityXi’an 710072China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China

1 Introduction The process of complex diseases is closely linked to the disruption of key biological pathways,it is crucial to identify the dysfunctional pathways and quantify the degree of dysregulation at the indivi... 详细信息

关键词： pathway activity dysregulation complex diseases biological pathways disruption key biological pathwaysit identify dysfunctional pathways

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Location Recommendation for Urban Facility Placement via Graph Convolutional and Recurrent Networks

引用

Journal of computer science & Technology 2024年第6期39卷 1419-1440页

作者： Pu Wang Jian-Jiang Lu Wei Chen Peng-Peng Zhao Lei Zhao Institute of Artificial Intelligence School of Computer Science and TechnologySoochow UniversitySuzhou 215006China Department of Data Resource and Information Development Soochow UniversitySuzhou 215006China

The ability to recommend candidate locations for service facility placement is crucial for the success of urban planning. Whether a location is suitable for establishing new facilities is largely determined by its potential popularity. However, it is a non-trivial task to predict popularity of candidate locations due to three significant challenges: 1) the spatio-temporal behavior correlations of urban dwellers, 2) the spatial correlations between candidate locations and existing facilities, and 3) the temporal auto-correlations of locations themselves. To this end, we propose a novel semi-supervised learning model, Spatio-Temporal Graph Convolutional and Recurrent Networks (STGCRN), aiming for popularity prediction and location recommendation. Specifically, we first partition the urban space into spatial neighborhood regions centered by locations, extract the corresponding features, and develop the location correlation graph. Next, a contextual graph convolution module based on the attention mechanism is introduced to incorporate local and global spatial correlations among locations. A recurrent neural network is proposed to capture temporal dependencies between locations. Furthermore, we adopt a location popularity approximation block to estimate the missing popularity from both the spatial and temporal domains. Finally, the overall implicit characteristics are concatenated and then fed into the recurrent neural network to obtain the ultimate popularity. The extensive experiments on two real-world datasets demonstrate the superiority of the proposed model compared with state-of-the-art baselines.

关键词： location recommendation popularity prediction spatio-temporal correlation deep learning

来源：评论

学校读者我要写书评

暂无评论

research progress of slippage characteristic and gas film stability enhancement methods on biomimetic hydrophobic surfaces

引用

Journal of Hydrodynamics 2024年第1期36卷 87-101页

作者： Meng-zhuo Zhang Hai-bao Hu Liu-zhen Ren Lu-yao Bao Jun Wen Luo Xie School of Marine Science and Technology Northwestern Polytechnical UniversityXi’an710072China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518063China

The biomimetic hydrophobic surface is a potentially efficient underwater drag reduction method and the drag reduction mechanism of this kind of surface comes from the interfacial *** now,it is a hotspot to grasp the slippage characteristic and explore slippage enhancement *** paper not only summarizes our numerical simulation and experimental results of slippage characteristic at the solid-liquid interface(SLI)of hydrophobic surfaces(HS)and the gas-liquid interface(GLI)of superhydrophobic surfaces(SHS)in recent years,but also introduces some innovative methods that can effectively improve the gas film stability and drag reduction effect of ***,we used the molecular dynamics(MD)simulation method to figure out the effect of the solid-liquid interaction strength,the system temperature and the shear rate on the slippage of SLI,and expound their action mechanism from molecular ***,by MD and multibody dissipative particle dynamics(MDPD)method,the slippage behavior at the GLI was studied under the influence of the microstructure size and the flow driving *** proposed a new kind of hybrid slip boundary condition model to describe the slippage characteristic on *** addition,we found through experiment that a three-dimensional backflow will appear on the GLI under the interfacial adsorption of surfactants,and the backflow direction will reverse with the change of GLI ***,we put forward the wettability step structure and gas injection method to enhance the stability and drag reduction effect of the gas film on SHS.

关键词： Hydrophobic surface superhydrophobic surface interfacial slip underwater drag reduction

来源：评论

学校读者我要写书评

暂无评论

A topical VAEGAN-IHMM approach for automatic story segmentation

引用

Mathematical Biosciences and Engineering 2024年第7期21卷 6608-6630页

作者： Yu, Jia Peng, Huiling Wang, Guoqiang Shi, Nianfeng School of Computer and Information Engineering Luoyang Institute of Science and Technology China Software Research Institute Technological University of Shannon Ireland

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance. © 2024 the Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：