检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiao, Yang Chen, Shaoxiang Jie, Zequn Chen, Jingjing Ma, Lin Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Meituan

Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities of LMMs. The current methods follow the paradigm of adapting the visual task outputs to language-oriented formats. This adaptation leads to the convenient development of such LMMs with minimal modifications, however, it overlooks the intrinsic characteristics of diverse visual tasks and hinders the learning of perception capabilities. To address this issue, we propose a novel LMM architecture named Lumen, which decouples the learning of perception capabilities into task-agnostic and task-specific stages. Firstly, Lumen promotes fine-grained vision-language concept alignment, which is the fundamental capability for various visual tasks. Thus the output of the task-agnostic stage is a shared representation for all vision-centric tasks we address in this paper. Afterward, the task-specific decoding is carried out by flexibly routing the shared representation to lightweight task decoders with negligible training efforts. Comprehensive experimental results on a series of vision-centric and VQA benchmarks indicate that our Lumen model not only achieves or surpasses the performance of existing LMM-based approaches in a range of vision-centric tasks while maintaining general visual understanding and instruction following capabilities. © 2024, CC BY-NC-SA.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Designing Novel Cognitive Diagnosis Models via Evolutionary Multi-Objective Neural Architecture Search

arXiv

引用

arXiv 2023年

作者： Yang, Shangshang Ma, Haiping Zhen, Cheng Tian, Ye Zhang, Limiao Jin, Yaochu Zhang, Xingyi The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230039 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Anhui Hefei230601 China The Faculty of Technology Bielefeld Unversity Bielefeld33619 Germany

Cognitive diagnosis plays a vital role in modern intelligent education platforms to reveal students’ proficiency in knowledge concepts for subsequent adaptive tasks. However, due to the requirement of high model interpretability, existing manually designed cognitive diagnosis models hold too simple architectures to meet the demand of current intelligent education systems, where the bias of human design also limits the emergence of effective cognitive diagnosis models. In this paper, we propose to automatically design novel cognitive diagnosis models by evolutionary multiobjective neural architecture search (NAS). Specifically, we observe existing models can be represented by a general model handling three given types of inputs and thus first design an expressive search space for the NAS task in cognitive diagnosis. Then, we propose multi-objective genetic programming (MOGP) to explore the NAS task’s search space by maximizing model performance and interpretability. In the MOGP design, each architecture is transformed into a tree architecture and encoded by a tree for easy optimization, and a tailored genetic operation based on four sub-genetic operations is devised to generate offspring effectively. Besides, an initialization strategy is also suggested to accelerate the convergence by evolving half of the population from existing models’ variants. Experiments on two real-world datasets demonstrate that the cognitive diagnosis models searched by the proposed approach exhibit significantly better performance than existing models and also hold as good interpretability as human-designed models. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

arXiv

引用

arXiv 2024年

作者： Gong, Chao Chen, Kai Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often exhibit incomplete erasure, consume a lot of computing resources, and inadvertently damage generation ability. In this work, we introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. Specifically, RECE efficiently leverages a closed-form solution to derive new target embeddings, which are capable of regenerating erased concepts within the unlearned model. To mitigate inappropriate content potentially represented by derived embeddings, RECE further aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts. Besides, to preserve the model’s generation ability, RECE introduces an additional regularization term during the derivation process, resulting in minimizing the impact on unrelated concepts during the erasure process. All the processes above are in closed-form, guaranteeing extremely efficient erasure in only 3 seconds. Benchmarking against previous approaches, our method achieves more efficient and thorough erasure with minor damage to original generation ability and demonstrates enhanced robustness against red-teaming tools. Code is available at https://***/CharlesGong12/RECE. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

High Common-Mode Rejection Differential Filter Based on Coupled Lines

High Common-Mode Rejection Differential Filter Based on Coup...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Zhen Liu Haoran Zhu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

In this paper, a differential bandpass filter (BPF) based on enhanced coupling line structure has been suggested in this study. Two out-of-band transmission zeros are added to the differential mode by loading the coupling line at the output terminal, which raises the rectangular coefficient of the filter. Two common mode transmission zeros in the passband are additionally provided by the open/short stub that is already loaded at the output port. To accommodate the demands of various filter performances, the location of the transmission zeros can be modified by altering the values of the coupling lines' and stubs' impedances. Finally, the passband common mode suppression might be as high as 40 dB.

关键词： Band-pass filters Couplings Radio frequency Conferences Loading Microwave circuits Filtering theory

来源：评论

学校读者我要写书评

暂无评论

SimDA: Simple Diffusion Adapter for Efficient Video Generation

SimDA: Simple Diffusion Adapter for Efficient Video Generati...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhen Xing Qi Dai Han Hu Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast, Text-to- Video (T2V) still falls short of expectations though attracting increasing interest. Existing works either train from scratch or adapt large T2I model to videos, both of which are computation and re-source expensive. In this work, we propose a Simple Dif-fusion Adapter (SimDA) that fine-tunes only 24M out of *** parameters of a strong T2I model, adapting it to video generation in a parameter-efficient way. In particular, we turn the T2I model for T2V by designing light-weight spatial and temporal adapters for transfer learning. Besides, we change the original spatial attention to the proposed Latent-Shift Attention (LSA) for temporal consistency. With a similar model architecture, we further train a video super-resolution model to generate high-definition (1024 x 1024) videos. In addition to T2V generation in the wild, SimDA could also be utilized in one-shot video editing with only 2 minutes tuning. Doing so, our method could minimize the training effort with extremely few tunable parameters for model adaptation.

关键词： Training Adaptation models Computational modeling Transfer learning Superresolution Text to image Diffusion models

来源：评论

学校读者我要写书评

暂无评论

ϵ-π: A Nonparametric Model for Neural Power Spectra Decomposition

引用

IEEE Journal of Biomedical and Health Informatics 2024年第5期28卷 2624-2635页

作者： Hu, Shiang Zhang, Zhihao Zhang, Xiaochu Wu, Xiaopei Valdes-Sosa, Pedro A. Anhui University Anhui Provincial Key Lab of Multimodal Cognitive Computation Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China University of Science and Technology of China School of Humanities and Social Science Department of Psychology Hefei230026 China University of Electronic Science and Technology of China MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China

The power spectra estimated from the brain recordings are the mixed representation of aperiodic transient activity and periodic oscillations, i.e., aperiodic component (AC) and periodic component (PC). Quantitative neurophysiology requires precise decomposition preceding parameterizing each component. However, the shape, statistical distribution, scale, and mixing mechanism of AC and PCs are unclear, challenging the effectiveness of current popular parametric models such as FOOOF, IRASA, BOSC, etc. Here, was proposed to decompose the neural spectra by embedding the nonparametric spectra estimation with penalized Whittle likelihood and the shape language modeling into the expectation maximization framework. was validated on the synthesized spectra with loss statistics and on the sleep EEG and the large sample iEEG with evaluation metrics and neurophysiological evidence. Compared to FOOOF, both the simulation presenting shape irregularities and the batch simulation with multiple isolated peaks indicated that improved the fit of AC and PCs with less loss and higher F1-score in recognizing the centering frequencies and the number of peaks;the sleep EEG revealed that produced more distinguishable AC exponents and improved the sleep state classification accuracy;the iEEG showed that approached the clinical findings in peak discovery. Overall, offered good performance in the spectra decomposition, which allows flexible parameterization using descriptive statistics or kernel functions. is a seminal tool for brain signal decoding in fields such as cognitive neuroscience, brain-computer interface, neurofeedback, and brain diseases. © 2013 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Metasurface-Based Wideband High Isolation Circularly Polarized Antenna For 5G MIMO Millimeter-Wave Systems

A Metasurface-Based Wideband High Isolation Circularly Polar...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Hui Zhu Haoran Zhu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

A wideband high isolation circularly polarized antenna for 5G MIMO millimeter-wave systems is presented in this paper. The presented antenna exhibits wideband characteristics due to the resonance of surface waves along the metasurface. The circularly polarized preliminary bandwidth is achieved by truncated corner patches when the truncation can be adjusted to implement the phase and amplitude values of the two quadrature modes. The port isolation is improved by the resonance of double-layer microstrip lines in the frequency. The size of the antenna is 17.8×17.8×1.02 mm 3 , the impedance bandwidth is 30.4% (23.29-31.66 GHz) and the 3-dB axial ratio bandwidth is 20.5% (24.47-30.12 GHz). In addition, the port isolation of the presented antenna is higher than 25 dB, and the peak gain is 8.4 dB. Therefore, the given antenna has the advantages of wideband, circularly polarized and high isolation.

关键词： Microwave antennas Surface impedance 5G mobile communication Surface waves Metasurfaces Broadband antennas Impedance

来源：评论

学校读者我要写书评

暂无评论

Non-autoregressive machine translation with probabilistic context-free grammar 23

Non-autoregressive machine translation with probabilistic co...

引用

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Shangtong Gui Chenze Shao Zhengrui Ma Xishan Zhang Yunji Chen Yang Feng State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://***/ictnlp/PCFG-NAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Squared-Sine Function and ANM DOA Estimation for RIS-Based Sensing Systems

TechRxiv

引用

TechRxiv 2023年

作者： Li, Yingsong Yu, Canping Li, Liping Huang, Zhixiang Wu, Qingqing The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei230601 China The Department of Electronic Engineering Shanghai Jiao Tong University 200240 China

Reconfigurable intelligent surface (RIS) is an emerging technology for improving the performance of wireless communications. In this letter, a joint Squared-Sine function and atomic norm minimization (ANM), denoted as SS-ANM, is proposed for passive sensing assisted by RIS in wireless communication systems interfered by a wireless access point (AP). The proposed joint optimization is used to estimate the targets’ direction-of-arrival (DOA), employing the spatial domain sparsity of the received signals. The optimal solution is achieved from the alternating direction method of multipliers (ADMM). With the help of the Squared-Sine function as the cost function, the proposed solution provides better estimation accuracy under various noises besides Gaussian noise, and meanwhile requires a lower computation complexity. Simulation results verify the superiority of the proposed joint minimization over existing DOA estimation methods. © 2023, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

High Degree of Freedom Low Coupling Sparse MIMO Array

High Degree of Freedom Low Coupling Sparse MIMO Array

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Yichang Yao Baohe Pang Yingsong Li Canping Yu Wudang Xiao Liping Li Nikola Zlatanov College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China Faculty of Computer and Engineering Sciences Innopolis University Innopolis Russia

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

To achieve high precision direction-of-arrival estimation of MIMO arrays in highly coupled environments, based on the difference and cooperative array principles, the uniform array fitted with 5 base layer array and the uniform array fitted with 6 base layer array were used as transmitting arrays, and with the addition of 1 base layer layer sparse array as receiving array, two sparse multi-in multiple-out arrays were designed for single-base radar, which have the characteristics of low coupling of transmitting array and high freedom of receiving array.

关键词： Couplings Direction-of-arrival estimation Accuracy Target recognition Fitting Estimation Radar

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：