检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Jiaming Yang, Senqiao Jia, Peidong Zhang, Renrui Lu, Ming Guo, Yandong Xue, Wei Zhang, Shanghang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China AI2Robotics China The Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Hong Kong

Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and maintain the model plasticity, we design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Specifically, we first comprehensively explore the different domain representations of the adapters with trainable high-rank or low-rank embedding spaces. Then we inject ViDAs into the pre-trained model, which leverages high-rank and low-rank features to adapt the current domain distribution and maintain the continual domain-shared knowledge, respectively. To exploit the low-rank and high-rank ViDAs more effectively, we further propose a Homeostatic Knowledge Allotment (HKA) strategy, which adaptively combines different knowledge from each ViDA. Extensive experiments conducted on four widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions. Project page: https://***/view/iclr2024-vida/home Copyright © 2023, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Multi-Objective Neural Architecture Search Approach to Advancing Cognitive Diagnosis in Intelligent Education

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Yang, Shangshang Ma, Haiping Bi, Ying Tian, Ye Zhang, Limiao Jin, Yaochu Zhang, Xingyi School of Artificial Intelligence Anhui University Hefei China Institutes of Physical Science and Information Technology Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China School of Electrical and Information Engineering Computational Intelligence Laboratory Zhengzhou University Zhengzhou China School of Computer Science and Technology Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei Anhui China School of Engineering Westlake University Hangzhou China

As a pivotal technique in intelligent education systems, cognitive diagnosis (CD) serves to reveal students’ knowledge proficiency for better tackling subsequent tasks. Unfortunately, due to pursuing high model interpretability, existing manually designed models for CD often hold simplistic architectures, which cannot cope with intricate data in modern education platforms. Furthermore, the bias of human design limits the emergence of novel and effective CD models. To develop interpretable and more effective models, thus this paper proposes an evolutionary multi-objective neural architecture search (NAS) approach for CD. Specifically, we first adopt a comprehensive search space for the NAS task of CD: all candidate models can be encompassed by a general model that deals with three distinct types of inputs. Then, an innovative model interpretability objective is devised to formulate the architecture search task as a bi-objective optimization problem (BOP). To solve the BOP, we employ a multi-objective genetic programming (MOGP) as the search strategy to explore the search space. To make the employed MOGP search well, all architectures are first encoded by trees for easy optimization, and we devise a genetic operation and a population initialization strategy to expedite its convergence. Finally, the proposed approach is actually a MOGP-based NAS approach for CD. Extensive experiments show that CD models searched by the proposed approach exhibit significantly better performance than existing models and hold as good interpretability as handcrafted models. Besides, the effectiveness of the proposed MOGP search strategy, the devised objective, and tailored strategies are validated. IEEE

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Coherence-Based Distributed Document Representation Learning for Scientific Documents

arXiv

引用

arXiv 2022年

作者： Tan, Shicheng Zhao, Shu Zhang, Yanping Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Province 230601 China School of Computer Science and Technology Anhui University Anhui Province Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Province 230601 China

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take into account the coherence of the document as a whole, e.g., a relation between the paper title and abstract, headline and description, or adjacent bodies in the document. The coherence shows whether a document is meaningful, both logically and syntactically, especially in scientific documents (papers or patents, etc.). In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document. First, we divide the document into two parts (e.g., title and abstract, etc) which construct a coupled text pair. Then, we adopt negative sampling to construct uncoupled text pairs whose two parts are from different documents. Finally, we train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents. We perform experiments on three datasets for one information retrieval task and two recommendation tasks. The experimental results verify the effectiveness of the proposed CTPE model. Copyright © 2022, The Authors. All rights reserved.

关键词： information retrieval

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study

Evaluating the Performance to Detecting Topic Shift of Large...

引用

6th International Conference on Intelligent Computing and Signal processing (ICSP)

作者： Pingfang Tian Deting Liu Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor.

关键词： Technological innovation Large language models Oral communication Signal processing Chatbots Context modeling

来源：评论

学校读者我要写书评

暂无评论

Spectral transfer-learning-based metasurface design assisted by complex-valued deep neural network

引用

Advanced Photonics Nexus 2024年第2期3卷 8-17页

作者： Yi Xu Fu Li Jianqiang Gu Zhiwei Bi Bing Cao Quanlong Yang Jiaguang Han Qinghua Hu Weili Zhang Tianjin University Center for Terahertz Waves and College of Precision Instrument and Optoelectronics EngineeringMinistry of EducationKey Laboratory of Optoelectronic Information TechnologyTianjinChina Tianjin University College of Intelligence and ComputingTianjinChina Central South University School of Physics and ElectronicsHunan Key Laboratory of Nanophotonics and DevicesChangshaChina Guilin University of Electronic Technology School of Optoelectronic EngineeringGuangxi Key Laboratory of Optoelectronic Information ProcessingGuilinChina Oklahoma State University School of Electrical and Computer EngineeringStillwaterOklahomaUnited States

Recently,deep learning has been used to establish the nonlinear and nonintuitive mapping between physical structures and electromagnetic responses of meta-atoms for higher computational ***,to obtain sufficiently accurate predictions,the conventional deep-learning-based method consumes excessive time to collect the data set,thus hindering its wide application in this interdisciplinary *** introduce a spectral transfer-learning-based metasurface design method to achieve excellent performance on a small data set with only 1000 samples in the target waveband by utilizing open-source data from another spectral *** demonstrate three transfer strategies and experimentally quantify their performance,among which the“frozen-none”robustly improves the prediction accuracy by∼26%compared to direct *** propose to use a complex-valued deep neural network during the training process to further improve the spectral predicting precision by∼30%compared to its real-valued *** design several typical teraherz metadevices by employing a hybrid inverse model consolidating this trained target network and a global optimization *** simulated results successfully validate the capability of our *** work provides a universal methodology for efficient and accurate metasurface design in arbitrary wavebands,which will pave the way toward the automated and mass production of metasurfaces.

关键词： transfer learning complex-valued deep neural network metasurface inverse design conditioned adaptive particle swarm optimization terahertz

来源：评论

学校读者我要写书评

暂无评论

Several progress of semi-supervised learning

引用

Journal of information and Computational Science 2009年第1期6卷 211-217页

作者： Ding, Shifei Su, Chunyang Jia, Weikuan Jin, Fengxiang Shi, Zhongzhi School of Computer Science and Technology China University of Mining and Technology Xuzhou 221008 China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Beijing 100080 China College of Plant Protection Shandong Agricultural University Taian 271018 China College of Geoinformation Science and Engineering Shandong University of Science and Technology Qingdao 266510 China

In this paper we discuss several progress of semi-supervised learning, making emphasis on semi-supervised classification. First, we introduce the history and basic concept and methods of semi-supervised learning, then explain the algorithms of semi-supervised learning in details, and discuss the current situation of semi-supervised learning, at last we look forward to the development trend of semi-supervised learning. © 2009 Binary information Press.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hypergraph-enhanced dual semi-supervised graph classification 24

Hypergraph-enhanced dual semi-supervised graph classificatio...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wei Ju Zhengyang Mao Siyu Yi Yifang Qin Yiyang Gu Zhiping Xiao Yifan Wang Xiao Luo Ming Zhang School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab Peking University China School of Statistics and Data Science Nankai University China Department of Computer Science University of California Los Angeles School of Information Technology & Management University of International Business and Economics China

In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to model higher-order dependencies among nodes. To tackle these challenges, we propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification, which captures graph semantics from the perspective of the hypergraph and the line graph, respectively. Specifically, to better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies beyond pairwise relations. Meanwhile, based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges, thereby better mining the underlying semantic structures. Finally, we develop a relational consistency learning to facilitate knowledge transfer between the two branches and provide better mutual guidance. Extensive experiments on real-world graph datasets verify the effectiveness of the proposed method against existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Secrecy Performance of MISO SWIPT Systems with TAS and Imperfect CSI

On Secrecy Performance of MISO SWIPT Systems with TAS and Im...

引用

作者： Pan, Gaofeng Lei, Hongjiang Deng, Yansha Fan, Lisheng Yang, Jing Chen, Yunfei Ding, Zhiguo Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing School of Electronic and Information Engineering Southwest University Chongqing400715 China School of Computing and Communications Lancaster University LancasterLA14YW United Kingdom Chongqing Key Laboratory of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Centre for Telecommunications King's College London LondonWC2R2LS United Kingdom School of Computer Science and Educational Software Guangzhou University Guangzhou510000 China Department of Electronic Engineering Shantou University Guangdong515063 China School of Information Engineering Yangzhou University Yangzhou225009 China School of Engineering University of Warwick CoventryCV47AL United Kingdom

In this paper, a multiple-input single-output (MISO) simultaneous wireless information and power transfer (SWIPT) system, including one base station (BS) equipped with multiple antennas, one desired single-antenna information receiver (IR), and N (N > 1) single-antenna energy-harvesting receivers (ERs) is considered. Assuming that the information signal to the desired IR may be eavesdropped by ERs if ERs are malicious, we investigate the secrecy performance of the target MISO SWIPT system when imperfect channel state information (CSI) is available and adopted for transmit antenna selection at the BS. Considering that each eavesdropping link experiences independent but not necessarily identically distributed Rayleigh fading, the closed-form expressions for the exact and the asymptotic secrecy outage probability, and the average secrecy capacity are derived and verified by simulations. Furthermore, the optimal power splitting factor is derived for each ER to realize the tradeoff between the energy harvesting and the information eavesdropping. Our results reveal the impact of the imperfect CSI on the secrecy performance of MISO SWIPT systems in the presence of multiple wiretap channels. © 2016 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition for In-the-wild Videos

Facial Expression Recognition for In-the-wild Videos

引用

International Conference on Automatic Face and Gesture Recognition

作者： Hanyu Liu Jiabei Zeng Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

In this paper, we propose a method for facial expression recognition for in-the-wild videos. Our method combines Deep Residual Network (ResNet) and Bidirectional Recurrent Neutral Network with Long-Short-Term Memory Unit (BLSTM). This method won the 2 nd place in the seven basic expression classification track of Affective Behavior Analysis in-the-wild Competition held in conjunction with the IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2020, achieving 66.9% accuracy and 40.8% final metric on the test set. We also visualize the learned attention maps and analyze the importance of different regions in facial expression recognition.

关键词： Face recognition Videos Feature extraction Training Conferences computer vision Mouth

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

IEEE International Conference on Electronic information and Communication technology (ICEICT)

作者： Yang Zhen Junwei Qi Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost.

关键词：

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：