检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Ma, Yi Hao, Jianye Hu, Xiaohan Zheng, Yan Xiao, Chenjun School of Computer and Information Technology Shanxi University China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education China College of Intelligence and Computing Tianjin University China Noah's Ark Lab Huawei Canada The Chinese University of Hong Kong Shenzhen China

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its ability to learn an effective control policy that seamlessly aligns with the inherent distribution of offline data. Unfortunately, behavior regularization, a simple yet effective offline RL algorithm, tends to struggle in this regard. In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. Our key observation is that by iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement, while also implicitly avoiding querying out-of-sample actions to prevent catastrophic learning failures. We prove that in the tabular setting this algorithm is capable of learning the optimal policy covered by the offline dataset, commonly referred to as the in-sample optimal policy. We then explore several implementation details of the algorithm when function approximations are applied. The resulting algorithm is easy to implement, requiring only a few lines of code modification to existing methods. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks, clearly demonstrate its superiority over behavior regularization. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatially Informed Independent vector analysis for Source Extraction based on the convolutive Transfer Function Model 48

Spatially Informed Independent vector analysis for Source Ex...

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Wang, Xianrui Brendel, Andreas Huang, Gongping Yang, Yichen Kellermann, Walter Chen, Jingdong Northwestern Polytechnical University CIAIC and Shaanxi Provincial Key Laboratory of Artificial Intelligence Xi'an710072 China Friedrich-Alexander-Universität Multimedia Communications and Signal Processing Erlangen-Nürnberg Germany

ISBN: (纸本)9781728163277

Spatial information can help improve source separation performance. Numerous spatially informed source extraction methods based on the independent vector analysis (IVA) have been developed, which can achieve reasonably good performance in non- or weakly reverberant environments. However, the performance of those methods degrades quickly as the reverberation increases. The underlying reason is that those methods are derived based on the multiplicative transfer function model with a rank-1 assumption, which does not hold true if reverberation is strong. To circumvent this issue, this paper proposes to use the convolutive transfer function (CTF) model to improve the source extraction performance and develop a spatially informed IVA algorithm. Simulations demonstrate the efficacy of the developed method even in highly reverberant environments. © 2023 IEEE.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

A Relay Buffer Prediction Method Based on LSTM in Terminal Cooperative Communication 23

A Relay Buffer Prediction Method Based on LSTM in Terminal C...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Fei, Jie Zhi, Hui Tie, Kui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China School of Electronic and Information Engineering Anhui University Hefei China CO. Ltd Bengbu China

ISBN: (纸本)9798350325959

In terminal cooperative communication, relay assisted communication with buffer has significant advantages in improving system throughput, signal-to-noise ratio, and reducing system outage probability. The existing relay methods with buffer are all fixed buffer method with a fixed size of the buffer and only considering relay wholehearted cooperation and forwarding, that is, all buffer of the relay assists communication. However, when the forwarding task is small and there is a large idle in forwarding buffer, the buffer area cannot be fully utilized. When the forwarding task is large and forwarding buffer is busy, packet loss may occur in the forwarding task. In order to improve the usage efficiency of relay buffer and reduce packet loss, this paper proposes a relay buffer prediction method based on the long short-term memory network to predict the amount of data that the relay needs to forward. According to the prediction, the size of the relay buffer is divided, so that the buffer can be dynamically adjusted on demand. Simulation results show that, compared with the fixed buffer method, the relay buffer prediction method has a better buffer usage efficiency and a lower packet loss rate. © 2023 IEEE.

关键词： Buffer Forecast LSTM Relay

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Neural Networks Pruning: Trimming for Reducing Memory or Workload

An Empirical Study on Neural Networks Pruning: Trimming for ...

引用

Data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Kaiwen Xiao Xiaodong Cai Ke Xu School of Artificial Intelligence Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei China

Most of existing studies on neural network pruning only consider memory-based pruning strategies. However pruning for computational workload is often more important in hardware deployments due to a greater focus on model computation reductions. In addition, most pruning schemes restore model accuracy during pruning at the expense of adding hyperparameters, extending training time and training complexity. This work proposes a statistical-based globally soft iterative pruning scheme. With little extra calculation, an extremely sparse model can be obtained without additional hyperparameters and extended training time. Moreover, this work proposes the concept of computational intensity to balance model memory and computational workload during pruning. Focusing on memory orientated pruning, we can achieve $\mathbf{303}\times, \mathbf{100}\times$ and $\mathbf{25}\times$ parameter compression on LeNet-5 (MNIST), VGG (CIFAR-10) and AlexNet (ImageNet) models, respectively. In particular, combined with cluster quantization, the LeNet-5 model parameters can be compressed to $\mathbf{3232}\times$ . Focusing on workload orientated pruning, we can reduce the computation by $\mathbf{7}.\mathbf{6}\times$ on the AlexNet model, without accuracy loss, significantly higher than prior work. In addition, in order to verify the versatility of the pruning method, we also migrate the pruning task to the object detection and implement $\mathbf{10}\times$ parameter compression and $\mathbf{2}.\mathbf{8}\times$ computation compression for YOLOv2 with reduced mAP within 1%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Client-tailored Adapter for Medical Image Segmentation

arXiv

引用

arXiv 2025年

作者： Hu, Guyue Song, Siyuan Kang, Yukun Yin, Zhu Zhao, Gangming Li, Chenglong Tang, Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China School of Internet Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Department of Computer Science The University of Hong Kong Hong Kong

Medical image segmentation in X-ray images is beneficial for computer-aided diagnosis and lesion localization. Existing methods mainly fall into a centralized learning paradigm, which is inapplicable in the practical medical scenario that only has access to distributed data islands. Federated Learning has the potential to offer a distributed solution but struggles with heavy training instability due to client-wise domain heterogeneity (including distribution diversity and class imbalance). In this paper, we propose a novel Federated Client-tailored Adapter (FCA) framework for medical image segmentation, which achieves stable and client-tailored adaptive segmentation without sharing sensitive local data. Specifically, the federated adapter stirs universal knowledge in off-the-shelf medical foundation models to stabilize the federated training process. In addition, we develop two client-tailored federated updating strategies that adaptively decompose the adapter into common and individual components, then globally and independently update the parameter groups associated with common client-invariant and individual client-specific units, respectively. They further stabilize the heterogeneous federated learning process and realize optimal client-tailored instead of sub-optimal global-compromised segmentation models. Extensive experiments on three large-scale datasets demonstrate the effectiveness and superiority of the proposed FCA framework for federated medical segmentation. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Graph Prompt Clustering

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年第7期47卷 5794-5805页

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning530219 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Beijing100816 China South China Technology Commercialization Center Guangzhou510006 China Guangdong University of Technology School of Information Engineering Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Guangzhou510033 China Ministry of Education Beijing100044 China

Due to the wide existence of unlabeled graph-structured data (e.g., molecular structures), the graph-level clustering has recently attracted increasing attention, whose goal is to divide the input graphs into several disjoint groups. However, the existing methods habitually focus on learning the graphs embeddings with different graph reguralizations, and seldom refer to the obvious differences in data distributions of distinct graph-level datasets. How to characteristically consider multiple graph-level datasets in a general well-designed model without prior knowledge is still challenging. In view of this, we propose a novel Graph Prompt Clustering (GPC) method. Within this model, there are two main modules, i.e., graph model pretraining as well as prompt and finetuning. In the graph model pretraining module, the graph model is pretrained by a selected source graph-level dataset with mutual information maximization and self-supervised clustering regularization. In the prompt and finetuning module, the network parameters of the pretrained graph model are frozen, and a groups of learnable prompt vectors assigned to each graph-level representation are trained for adapting different target graph-level datasets with various data distributions. Experimental results across six benchmark datasets demonstrate the impressive generalization capability and effectiveness of GPC compared with the state-of-the-art methods. © 1979-2012 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic piano performance interaction system based on greedy algorithm for dexterous manipulator

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 473-485页

作者： Yufei WANG Junfeng YAO Yalan ZHOU Zefeng WANG Center for Digital Media Computing School of FilmXiamen UniversityXiamen 361005China Institute of Artificial Intelligence Xiamen UniversityXiamen 361005China School of Informatics Xiamen UniversityXiamen 361005China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen 361005China

With continuous advancements in artificial intelligence(AI), automatic piano-playing robots have become subjects of cross-disciplinary interest. However, in most studies, these robots served merely as objects of observation with limited user engagement or interaction. To address this issue, we propose a user-friendly and innovative interaction system based on the principles of greedy algorithms. This system features three modules: score management, performance control, and keyboard interactions. Upon importing a custom score or playing a note via an external device, the system performs on a virtual piano in line with user inputs. This system has been successfully integrated into our dexterous manipulator-based piano-playing device, which significantly enhances user interactions.

关键词： Human-robot interaction Piano-playing robot Greedy algorithm Score parsing

来源：评论

学校读者我要写书评

暂无评论

Cross Deployment of Active and Passive Reconfigurable Intelligent Surfaces (RISs) for Next-Generation Communications 5

Cross Deployment of Active and Passive Reconfigurable Intell...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Chen, Luqi Chung, Kwok L. Lai, Guoming Yao, Junhao Zou, Xiaopeng Cheng, Xin Zheng, Kangtai Li, Yingsong School of Computer Science and Engineering Huizhou University China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

In recent years, reconfigurable intelligent surface (RIS) technologies have been proposed due to its ability in shaping propagation environment for future 6G network development. Existing RIS technologies mainly include the active reconfigurable intelligent surface (ARIS) and the passive reconfigurable intelligent surface (PRIS). In this paper, according to the characteristics of RIS and demands of lower costs, we present a new strategy on the cross-deployment of ARIS and PRIS that meets the beneficial maximization in both capital cost and running cost. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A dual-band antenna designed for 5G communication based on a self-decoupled antenna

A dual-band antenna designed for 5G communication based on a...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Fang, Rongzhen Wu, Xianliang Chen, Zhipeng Dong, Mengying Hu, Yunfeng Li, Yuanyuan Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui University Department of Education of Anhui Province Hefei China

ISBN: (纸本)9781665452366

In this paper, a dual-band antenna for 5G communication based on an antenna design with self-decoupling properties is *** antenna is composed of a self-decoupled antenna unit vertically placed on an 30×80 mm2 ground plane and printed on 0.8 mm thick FR-4(ϵr = 4.4, tanδ = 0.02) substrate,and then added a pair of L-shaped coupling feeder structures on this *** shows that the antenna has two operating frequency bands of 3.3-4.2GHz and 4.8-5GHz, and has good transmission and isolation in the above two operating frequency ***,it also has the advantages of small size, self-decoupling,high isolation,simple structure and easy *** antenna can be used as 5G mobile phone communication antenna unit. © 2022 IEEE.

关键词： 5G mobile communication systems

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：