检索结果-内蒙古大学图书馆

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Hongxin Pan Chao Yang Yifei Yin Bin Liang Hao Shi Guanghui Wu Chongqing Innovation Center Beijing Institute of Technology Chongqing China Shanghai Institute of Satellite Engineering Shanghai China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The details regarding targets within Synthetic Aperture Radar (SAR) imagery are typically conveyed and maintained in complex-valued form. Namely, the information regarding both the amplitude and phase is essential. In the process of recognizing targets with SAR, the network only utilizes the amplitude image as input, while the phase information is neglected, resulting in poor recognition performance. This paper proposes a Feature Attention Complex-Valued-Based convolutional neural Network (FACV-Net) for SAR ship recognition to overcome these issues, which effectively utilizes phase information to improve target recognition. Firstly, to meet the requirements of network training in complex domains, a series of complex-valued operation blocks have been constructed. Moreover, a new complex-valued Attention Module (CAM) is introduced to ensure that the network focuses on the amplitude and phase characteristics of the target separately. Additionally, to address the mismatch problem between the amplitude and phase data, two distinct methods for complex-valued max-pooling are utilized. Ultimately, the performance of the proposed FACV-Net is assessed using the OpenSARship dataset, and the results indicate that this novel approach surpasses conventional networks in terms of recognition accuracy. When the CAM is added, the performance of the network sees a further enhancement of around 3% in accuracy. These findings confirm the proposed method’s effectiveness and advantage over others.

关键词： Training Image recognition Accuracy Target recognition Data processing Radar polarimetry Convolutional neural networks Marine vehicles Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling

arXiv

引用

arXiv 2024年

作者： Shi, Yuhui Sheng, Qiang Cao, Juan Mi, Hao Hu, Beizhe Wang, Danding Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Xi’an Jiaotong University China

With the rapidly increasing application of large language models (LLMs), their abuse has caused many undesirable societal problems such as fake news, academic dishonesty, and information pollution. This makes AI-generated text (AIGT) detection of great importance. Among existing methods, white-box methods are generally superior to black-box methods in terms of performance and generalizability, but they require access to LLMs’ internal states and are not applicable to black-box settings. In this paper, we propose to estimate word generation probabilities as pseudo white-box features via multiple re-sampling to help improve AIGT detection under the black-box setting. Specifically, we design POGER, a proxy-guided efficient re-sampling method, which selects a small subset of representative words (e.g., 10 words) for performing multiple re-sampling in black-box AIGT detection. Experiments on datasets containing texts from humans and seven LLMs show that POGER outperforms all baselines in macro F1 under black-box, partial white-box, and out-of-distribution settings and maintains lower re-sampling costs than its existing counterparts. © 2024, CC BY-NC-SA.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Automobile airbag defect detection algorithm based on improved Faster RCNN

Automobile airbag defect detection algorithm based on improv...

引用

2021 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2021

作者： Luo, Linjie Deng, Chengzhi Wu, Zhaoming Wang, Shengqian Ye, Tianyu School of Information Engineering Nanchang Institute of Technology Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang China

ISBN: (纸本)9781665439602

The traditional image processing method has a low detection rate for various kinds of automobile airbag surface defects in the production process, which is difficult to meet the actual demand of industrial production. In order to improve the detection rate of automobile airbag surface defects and meet the real-time requirements of industrial detection, this paper proposes an improved Faster RCNN deep learning algorithm. Firstly, the method adopts the E-FPN to enhance the feature extraction ability of the network for multi-scale targets. Then, ROI Align algorithm is introduced instead of ROI Pooling algorithm to improve the detection ability of small targets. Finally, the designed Light Head is used to improve the running speed of the network. The experimental results show that the average precision of the improved Faster RCNN algorithm for automobile airbag defect detection reaches 97.2%, and the detection time is 23.73 milliseconds, which is obviously superior to the original algorithm and has higher detection accuracy and practicability. © 2021 IEEE.

关键词： Surface defects

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

Industrial object detection method based on improved CenterNet

Industrial object detection method based on improved CenterN...

引用

2021 International Conference on Computer Engineering and Artificial Intelligence, ICCEAI 2021

作者： Tang, Cong Wu, Zhaoming Wang, Shengqian Deng, Chengzhi Luo, Linjie School of Information Engineering Nanchang Institute of Technology Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang China

ISBN: (纸本)9781665439602

Aiming at the contradiction between accuracy and speed in industrial object detection, this paper proposes an industrial object detection method based on improved CenterNet. The improved method uses ResNet-50 as the Backbone to boost detection speed, and an upsampling layer is added to the feature processing network to improve detection accuracy. The expermient results show that the mAP of the improved method reaches 87.41 %, which is 3.44% higher than the CenterNet-Res101 method, and the detection speed reaches 31 FPS, which is 4 FPS faster than the CenterNet-Res101 method. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Digital Adaptive Timing Mismatch Calibration for Sub-Nyquist Wideband Sampling

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Ma, Yuan Zheng, Yiling Zhang, Xingjian Liao, Bin Shenzhen University State Key Laboratory of Radio Frequency Heterogeneous Integration Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China Pengcheng Laboratory Shenzhen518055 China Shenzhen University College of Electronic and Information Engineering Shenzhen518060 China Harbin Institute of Technology Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Shenzhen518055 China Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China State Key Laboratory of Radio Frequency Heterogeneous Integration Shenzhen518060 China Fudan University Institute of Space Internet Shanghai China

The employment of sub-Nyquist sampling enables the adaptation to the ever-increasing bandwidth demands of wireless communication systems. Multicoset sampling is a nonuniform sub-Nyquist sampling technique that can be realized by using a multi-channel architecture. Nevertheless, the performance of multicoset sampling is significantly affected by timing mismatches among sub-ADCs. Traditional analog calibration scheme mitigates timing mismatch errors by adjusting the sampling clock in the front-end, but its performance is suboptimal due to the difficulty in selecting an appropriate initial step size and the sequential calibration process. In this paper, a data-driven digital adaptive timing mismatch calibration approach is proposed that uses real-time measurement data only to calculate calibration parameters without changing hardware circuits, making it effective for tracking variations in mismatches among multiple channels. Based on the nonlinear relationship between the timing mismatches and the normalized mean squared error of the output spectrum, the proposed data-driven calibration scheme jointly computes calibration parameters among multiple channels in parallel through a series of dynamic linearization data models with a time-varying pseudo-partial derivative parameter estimation procedure, and then adaptively adjusts the sampling matrix in the reconstruction to correct unwanted distortions in the output spectrum. To further improve the calibration performance, particle swarm optimization algorithm is exploited to generate parameter vectors used in the proposed data-driven calibration scheme. Numerical analyses indicate that the proposed data-driven digital calibration scheme can eliminate timing mismatches with fewer calibration iterations and enhanced accuracy. © 2015 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A 220-GHz Wireless Communication System Using a Quasi-Optical Cryogenic Receiver of High Sensitivity

A 220-GHz Wireless Communication System Using a Quasi-Optica...

引用

IEEE International Workshop on Radio-Frequency Integration technology (RFIT)

作者： Huanxin Li Dan Qiao Xindi Yu Liangbin Zhao Ziru Chen Heng Liu Xiang Gao School of Information and Electronics Beijing Institute of Technology Beijing China Division of Electronics and Information Metrology National Institute of Metrology Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9798331541095

ISBN: (纸本)9798331541101

This paper presents the design and implementation of a 220-GHz wireless communication system by using a quasi-optical cryogenic receiver of high sensitivity. The presented terahertz (THz) communication system utilizes a quasi-optical cryogenic receiver with a noise factor much lower than that of conventional room-temperature counterpart, thus helping to increase the transmission distance in long-range communication scenarios. In the scaled wireless link experiment, the communication data rate achieves 10 Gbit/s for a 16-quadrature amplitude modulation. According to the link budget, the communication distance can be around 5 km provided using appropriate transmitter power and antenna gains for practical scenarios. Considering the small volume, light weight and high sensitivity of the cryogenic receiver, the proposed system should be very useful for long-range THz communication applications.

关键词： Wireless communication Radio frequency Wireless sensor networks Sensitivity Transmitting antennas Radio transmitters Noise Receivers Cryogenics Terahertz communications

来源：评论

学校读者我要写书评

暂无评论

FIRE: a dataset for feedback integration and refinement evaluation of multimodal models 24

FIRE: a dataset for feedback integration and refinement eval...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traditional Mongolian-To-Cyrillic Mongolian Conversion Method Based on the Combination of Rules and Transformer 9

Traditional Mongolian-To-Cyrillic Mongolian Conversion Metho...

引用

9th IEEE International Conference on Cloud computing and Intelligence Systems, CCIS 2023

作者： Na, Muhan Bao, Feilong Wang, Weihua Gao, Guanglai Dulamragchaa, Uuganbaatar College of Computer Science Inner Mongolia University Hohhot010021 China Inner Mongolia University Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot010021 China Inner Mongolia University Natl. and Loc. Jt. Eng. Res. Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China Institute of Mathematics and Computer Science Mongolian Academy of Sciences Ulaanbaatar999097 Mongolia

ISBN: (纸本)9798350304428

Mongolian words are composed of stems and suffixes, resulting in a large vocabulary of Mongolian and many Out-of-vocabulary (OOV) words. Using only a dictionary cannot convert Traditional Mongolian OOV words. Therefore, this paper proposes a Traditional Mongolian to Cyrillic Mongolian conversion method based on combining rules and Transformer. This method uses rules based approach for converting in-vocabulary words and the Transformer model to convert OOV words. Experimental results show that using a Transformer outperforms the previous best OOV words conversion model, and the conversion method based on the combination of rules and Transformer has WER of 13.18%. © 2023 IEEE.

关键词： Mongolian translation Neural Network Self-Attention

来源：评论

学校读者我要写书评

暂无评论

Advancing Controllable Diffusion Model for Few-Shot Object Detection in Optical Remote Sensing Imagery

Advancing Controllable Diffusion Model for Few-Shot Object D...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tong Zhang Yin Zhuang Xinyi Zhang Guanqun Wang He Chen Fukun Bi National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Peking University Beijing China North China University of Technology Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Few-shot object detection (FSOD) from optical remote sensing imagery has to detect rare objects given only a few annotated bounding boxes. The limited training data is hard to represent the data distribution of realistic remote sensing scenes, restricting the performance of FSOD. Recently, learning conditional controls for text-to-image diffusion model has achieved great progress, which is capable of precisely generating the controllable yet imaginational images by text prompt and spatially localized input conditions. Accordingly, in this work, we aim to explore the potential of diffusion model and propose a solution for few-shot object detection by controllable data generation. Firstly, draw upon a few annotated objects, their bounding boxes and categories are respectively used as the spatial conditions and text prompts, then employ them into large text-to-image diffusion models for controlled image generation. Secondly, based the generated images, in order to adapt to the scale and orientation variances of remote sensing objects, a data transformation is devised for boosting the robustness of model training. Finally, some experiments were conducted on public remote sensing dataset DIOR, and the results proved its effectiveness.

关键词： Training Image synthesis Text to image Training data Object detection Diffusion models Optical imaging

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：