检索结果-内蒙古大学图书馆

From model to implementation: a network algorithm programming language

Science China(Information Sciences) 2020年第7期63卷 205-221页

作者： Jian WANG Jie AN Mingshuai CHEN Naijun ZHAN Lulin WANG Miaomiao ZHANG Ting GAN State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Engineering Tongji University Network Integration Technology Research Department Huawei Technologies Co. Ltd. School of Computer Science Wuhan University

software-defined networking(SDN) is a revolutionary technology that facilitates network management and enables programmatically efficient network configuration, thereby improving network performance and flexibility. However, as the application programming interfaces(APIs) of SDN are low-level or functionality-restricted, SDN programmers cannot easily keep pace with the ever-changing devices, topologies, and demands of SDN. By deriving motivation from industry practice, we define a novel network algorithm programming language(NAPL) that enhances the SDN framework with a rapid programming flow from topology-based network models to C++ implementations, thus bridging the gap between the limited capability of existing SDN APIs and the reality of practical network management. In contrast to several state-of-the-art languages, NAPL provides a range of critical high-level network programming features:(1) topology-based network modeling and visualization;(2) fast abstraction and expansion of network devices and constraints;(3) a declarative paradigm for the fast design of forwarding policies;(4) a built-in library for complex algorithm implementation;(5) full compatibility with C++ programming; and(6) userfriendly debugging support when compiling NAPL into highly readable C++ codes. The expressiveness and performance of NAPL are demonstrated in various industrial scenarios originating from practical network management.

关键词： software-defined networking(SDN) network algorithm programming language(NAPL) network abstraction

来源：评论

学校读者我要写书评

暂无评论

Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification

arXiv

引用

arXiv 2023年

作者： Liao, Minghui Wan, Guojia Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Determining the types of neurons within a nervous system plays a significant role in the analysis of brain connectomics and the investigation of neurological diseases. However, the efficiency of utilizing anatomical, physiological, or molecular characteristics of neurons is relatively low and costly. With the advancements in electron microscopy imaging and analysis techniques for brain tissue, we are able to obtain whole-brain connectome consisting neuronal high-resolution morphology and connectivity information. However, few models are built based on such data for automated neuron classification. In this paper, we propose NeuNet, a framework that combines morphological information of neurons obtained from skeleton and topological information between neurons obtained from neural circuit. Specifically, NeuNet consists of three components, namely Skeleton Encoder, Connectome Encoder, and Readout Layer. Skeleton Encoder integrates the local information of neurons in a bottom-up manner, with a one-dimensional convolution in neural skeleton’s point data;Connectome Encoder uses a graph neural network to capture the topological information of neural circuit;finally, Readout Layer fuses the above two information and outputs classification results. We reprocess and release two new datasets for neuron classification task from volume electron microscopy(VEM) images of human brain cortex and Drosophila brain. Experiments on these two datasets demonstrated the effectiveness of our model with accuracy of 0.9169 and 0.9363, respectively. Code and data are available at: https://***/WHUminghui/NeuNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Revisiting Knowledge Distillation for Autoregressive Language Models

arXiv

引用

arXiv 2024年

作者： Zhong, Qihuang Ding, Liang Shen, Li Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Sun Yat-sen University China Nanyang Technological University Singapore

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we empirically find that larger teachers might dramatically result in a poorer student. In response to this problem, we conduct a series of analyses and reveal that different tokens have different teaching modes, neglecting which will lead to performance degradation. Motivated by this, we propose a simple yet effective adaptive teaching approach (ATKD) to improve the KD. The core of ATKD is to reduce rote learning and make teaching more diverse and flexible. Extensive experiments on 8 LM tasks show that, with the help of ATKD, various baseline KD methods can achieve consistent and significant performance gains (up to +3.04% average score) across all model types and sizes. More encouragingly, ATKD can improve the student model generalization effectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2023年

作者： Guo, Haonan Su, Xin Wu, Chen Du, Bo Zhang, Liangpei The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China The School of Remote Sensing and Information Engineering Wuhan University Wuhan China The 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 Wuhan China

Change detection (CD) is a fundamental and important task for monitoring the land surface dynamics in the earth observation field. Existing deep learning-based CD methods typically extract bi-temporal image features using a weight-sharing Siamese encoder network and identify change regions using a decoder network. These CD methods, however, still perform far from satisfactorily as we observe that 1) deep encoder layers focus on irrelevant background regions and 2) the models' confidence in the change regions is inconsistent at different decoder stages. The first problem is because deep encoder layers cannot effectively learn from imbalanced change categories using the sole output supervision, while the second problem is attributed to the lack of explicit semantic consistency preservation. To address these issues, we design a novel similarity-aware attention flow network (SAAN). SAAN incorporates a similarity-guided attention flow module with deeply supervised similarity optimization to achieve effective change detection. Specifically, we counter the first issue by explicitly guiding deep encoder layers to discover semantic relations from bi-temporal input images using deeply supervised similarity optimization. The extracted features are optimized to be semantically similar in the unchanged regions and dissimilar in the changing regions. The second drawback can be alleviated by the proposed similarity-guided attention flow module, which incorporates similarity-guided attention modules and attention flow mechanisms to guide the model to focus on discriminative channels and regions. We evaluated the effectiveness and generalization ability of the proposed method by conducting experiments on a wide range of CD tasks. The experimental results demonstrate that our method achieves excellent performance on several CD tasks, with discriminative features and semantic consistency preserved. Copyright © 2023, The Authors. All rights reserved.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Building-Road Collaborative Extraction from Remote Sensing Images via Cross-Task and Cross-Scale Interaction

arXiv

引用

arXiv 2023年

作者： Guo, Haonan Su, Xin Wu, Chen Du, Bo Zhang, Liangpei The School of Remote Sensing and Information Engineering Wuhan University Wuhan China The 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 Wuhan China The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China

Buildings and roads are the two most basic man-made environments that carry and interconnect human society. Building and road information has important application value in the frontier fields of regional coordinated development, disaster prevention, auto-driving, etc. Mapping buildings and roads from very high-resolution (VHR) remote sensing images has become a hot research topic. However, the existing methods often extract buildings and roads with separate models, ignoring their strong spatial correlation. To fully utilize their complementary relation, we propose a method that simultaneously extracts buildings and roads from remote sensing images. The accuracy of both tasks can be improved using our proposed multi-task feature interaction and cross-scale feature interaction modules. To be specific, a multi-task interaction module is proposed to interact information across building extraction and road extraction tasks while preserving the unique information of each task. Furthermore, a cross-scale interaction module is designed to automatically learn the optimal reception field for buildings and roads under varied appearances and structures. Compared with existing methods that train individual models for each task separately, the proposed collaborative extraction method can utilize the complementary advantages between buildings and roads and reduce the inference time by half using a single model. Experiments on a wide range of urban and rural scenarios show that the proposed algorithm can achieve building-road extraction with outstanding performance and efficiency. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Robust Synthetic-to-Real Transfer for Stereo Matching

arXiv

引用

arXiv 2024年

作者： Zhang, Jiawei Li, Jiahe Huang, Lei Yu, Xiaohan Gu, Lin Zheng, Jin Bai, Xiao School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China SKLCCSE Institute of Artificial Intelligence Beihang University China School of Computing Macquarie University Australia RIKEN AIP Japan The University of Tokyo Japan

With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However, few studies have investigated the robustness after fine-tuning them in real-world scenarios, during which the domain generalization ability can be seriously degraded. In this paper, we explore fine-tuning stereo matching networks without compromising their robustness to unseen domains. Our motivation stems from comparing Ground Truth (GT) versus Pseudo Label (PL) for fine-tuning: GT degrades, but PL preserves the domain generalization ability. Empirically, we find the difference between GT and PL implies valuable information that can regularize networks during fine-tuning. We also propose a framework to utilize this difference for fine-tuning, consisting of a frozen Teacher, an exponential moving average (EMA) Teacher, and a Student network. The core idea is to utilize the EMA Teacher to measure what the Student has learned and dynamically improve GT and PL for fine-tuning. We integrate our framework with state-of-the-art networks and evaluate its effectiveness on several real-world datasets. Extensive experiments show that our method effectively preserves the domain generalization ability during fine-tuning. Code is available at: https://***/jiaw-z/DKT-Stereo. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AUTOMATICALLY ADJUSTABLE MULTI-SCALE FEATURE EXTRACTION FRAMEWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION

AUTOMATICALLY ADJUSTABLE MULTI-SCALE FEATURE EXTRACTION FRAM...

引用

2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

作者： Yang, Jiaqi Du, Bo Wu, Chen Zhang, Liangpei State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China 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 Wuhan430072 China

Recently, deep learning-based methods have shown the great potential in hyperspectral image (HSI) classification. Nevertheless, feature extraction by convolutional neural network (CNN) is often performed on only one scale, resulting in multi-scale information loss. To address this problem, in this paper, we propose an automatically adjustable multi-scale feature extraction framework (A2MFE-Framework) for hyperspectral classification, including a scale reference network and two scale transformation networks. With the well-designed architecture, A2MFE-Framework can not only extract multi-scale features, but also automatically change the network structure to match input features of different scales. Experimental results on two benchmark HSI datasets demonstrate that the A2MFE-Framework can better capture multi-scale features of different objects via an automatically adjustable feature extraction framework with higher classification accuracy compared with previous methods. ©2021 IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

HPCNet: A Hybrid Progressive Coupled network for Image Deraining

HPCNet: A Hybrid Progressive Coupled Network for Image Derai...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Qiong Wang Kui Jiang Jinyi Lai Zheng Wang Jianhui Zhang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Huawei Technologies Cloud BU College of Computer Science and Technology Hangzhou Dianzi University

Convolutional neural networks (CNNs) and Transformers have significantly succeeded in low-level vision tasks. Although prominent complementary characteristics exist regarding the larger receptive field and better convergence, only some efforts have compacted them efficiently due to their individual and nonnegligible weakness. In this paper, we propose a hybrid progressive coupled network (HPCNet) for rain perturbation removal, which integrates the advantages of these two architectures while maintaining both effectiveness and efficiency. In particular, we achieve the progressive decomposition and association of rain-free and rain features, designed as an asymmetrical dual-path mutual representation network to alleviate the computational cost. Meanwhile, we equip the network with high-efficiency convolutions and resolution rescaling strategy to trade off the computational complexity. Extensive experiments show that our method outperforms MPRNet on average while saving 87.2% and 61.1% of the computational cost and parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MANDARIN LOMBARD FLAVOR CLASSIFICATION

arXiv

引用

arXiv 2023年

作者： Liu, Qingmu Yang, Yuhong Li, Baifeng Chen, Hongyang Tu, Weiping Lin, Song National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan China Guangdong OPPO Mobile Telecommunications Corp. China

The Lombard effect refers to individuals’ unconscious modulation of vocal effort in response to variations in the ambient noise levels, intending to enhance speech intelligibility. The impact of different decibel levels and types of background noise on Lombard effects remains unclear. Building upon the characteristic of Lombard speech that individuals adjust their speech to improve intelligibility dynamically based on the self-feedback speech, we propose a flavor classification approach for the Lombard effect. We first collected Mandarin Lombard speech under different noise conditions, then simulated self-feedback speech, and ultimately conducted the statistical test on the word correct rate. We found that both SSN and babble noise types result in four distinct categories of Mandarin Lombard speech in the range of 30 to 80 dBA with different transition points. Copyright © 2023, The Authors. All rights reserved.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

arXiv

引用

arXiv 2023年

作者： Zhu, Miaoxi Shen, Li Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China The University of Sydney Australia

The growing size of available data has attracted increasing interest in solving minimax problems in a decentralized manner for various machine learning tasks. Previous theoretical research has primarily focused on the convergence rate and communication complexity of decentralized minimax algorithms, with little attention given to their generalization. In this paper, we investigate the primal-dual generalization bound of the decentralized stochastic gradient descent ascent (D-SGDA) algorithm using the approach of algorithmic stability under both convex-concave and nonconvex-nonconcave settings. Our theory refines the algorithmic stability in a decentralized manner and demonstrates that the decentralized structure does not destroy the stability and generalization of D-SGDA, implying that it can generalize as well as the vanilla SGDA in certain situations. Our results analyze the impact of different topologies on the generalization bound of the D-SGDA algorithm beyond trivial factors such as sample sizes, learning rates, and iterations. We also evaluate the optimization error and balance it with the generalization gap to obtain the optimal population risk of D-SGDA in the convex-concave setting. Additionally, we perform several numerical experiments which validate our theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

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：