检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Kai Wei, Zhipeng Chen, Jingjing Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

Recent research has demonstrated that Deep Neural Networks (DNNs) are vulnerable to adversarial patches which introduce perceptible but localized changes to the input. Nevertheless, existing approaches have focused on generating adversarial patches on images, their counterparts in videos have been less explored. Compared with images, attacking videos is much more challenging as it needs to consider not only spatial cues but also temporal cues. To close this gap, we introduce a novel adversarial attack in this paper, the bullet-screen comment (BSC) attack, which attacks video recognition models with BSCs. Specifically, adversarial BSCs are generated with a Reinforcement Learning (RL) framework, where the environment is set as the target model and the agent plays the role of selecting the position and transparency of each BSC. By continuously querying the target models and receiving feedback, the agent gradually adjusts its selection strategies in order to achieve a high fooling rate with non-overlapping BSCs. As BSCs can be regarded as a kind of meaningful patch, adding it to a clean video will not affect people's understanding of the video content, nor will arouse people's suspicion. We conduct extensive experiments to verify the effectiveness of the proposed method. On both UCF-101 and HMDB-51 datasets, our BSC attack method can achieve about 90% fooling rate when attacking three mainstream video recognition models, while only occluding © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Novel Sparse Array Design Based on the Maximum Inter-Element Spacing Criterion

TechRxiv

引用

TechRxiv 2022年

作者： Shi, Wanlu Li, Yingsong de Lamare, Rodrigo C. College of Information and Communication Engineering Harbin Engineering University Harbin150001 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China G¨¢vea Rio de Janeiro Brazil The University of York United Kingdom

A novel sparse array (SA) structure is proposed based on the maximum inter-element spacing (IES) constraint (MISC) criterion. Compared with the traditional MISC array, the proposed SA configurations, termed as improved MISC (IMISC) has significantly increased uniform degrees of freedom (uDOF) and reduced mutual coupling. In particular, the IMISC arrays are composed of six uniform linear arrays (ULAs), which can be determined by an IES set. The IES set is constrained by two parameters, namely the maximum IES and the number of sensors. The uDOF of the IMISC arrays is derived and the weight function of the IMISC arrays is analyzed as well. The proposed IMISC arrays have a great advantage in terms of uDOF against the existing SAs, while their mutual coupling remains at a low level. Simulations are carried out to demonstrate the advantages of the IMISC arrays. © , CC BY.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Denoiser-Guided Image Deconvolution with Arbitrary Boundaries and Incomplete Observations

SSRN

引用

SSRN 2023年

作者： He, Liangtian Gao, Shaobing Deng, Liang-Jian Wang, Yilun Wang, Chao Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China College of Computer Science Sichuan University Chengdu610065 China Chengdu611731 China American Family Insurance ChicagoIL60654 United States College of Mathematics Physics and Information Zhejiang Ocean University Zhoushan316022 China

Non-blind image deconvolution (NBID) has been a significant and long-standing research topic in the field of imaging sciences. While enduring efforts have been made over the past decades, they are extensively focusing on the scenario where the blur process is artificially assumed, e.g., typically under periodic boundary condition, as the involved matrix inversion can be efficiently tackled using the fast Fourier transforms (FFTs). However, despite its popularity, these boundary conditions are not always realistic assumptions and can lead to severe artifacts in the recovered image. Therefore, image deconvolution with arbitrary boundaries remains as a fundamental problem to be investigated. In this paper, we propose a principled framework with the aid of Plug-and-Play (PnP) scheme to address NBID in a more realistic scenario of unknown boundary. Specifically, the local and nonlocal denoiser priors with implicit optimization objectives are incorporated into a unified model, and the degradation operator is formulated as a composition of a convolution and a spatial mask. Two kinds of experiments: deconvolution, deconvolution with inpainting, all with unknown boundaries are tested. Both quantitative and qualitative evaluations demonstrate that the proposed denoiser-guided PnP framework is highly flexible and effective to cope with the general image deconvolution tasks. © 2023, The Authors. All rights reserved.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

A Novel Compensation Inductance Structure for Suppressing Differential-to-Common Mode Conversion in Bended Differential Transmission Line 8

A Novel Compensation Inductance Structure for Suppressing Di...

引用

8th Asia-Pacific Conference on Antennas and Propagation, APCAP 2019

作者： Wang, Jiabao Sun, Yufa Zhu, Haoran Li, Fan Anhui University Key Lab of Intelligent Computing Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665400541

A novel compact compensation inductance structure optimized by genetic algorithm (GA) for right-angle bended transmission line is proposed to mitigate differential-to-common mode conversion noise in this paper. In comparison with the previous suppression method, high suppression level and large bandwidth are obtained with the proposed structure. Simultaneously, the differential return loss and insertion loss have been minimized by GA, leading to an overall improved signal integrity (SI). Furthermore, the proposed structure places inside the transmission line and does not occupy extra wiring space. Finally, the differential-to-common mode conversion can be prohibited from DC to 11 GHz with a suppression level of-23.13 dB. The measured results agree well with the simulated ones. © 2019 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Compact ultra-wideband MIMO antenna with double notch 8

Compact ultra-wideband MIMO antenna with double notch

引用

8th Asia-Pacific Conference on Antennas and Propagation, APCAP 2019

作者： Wang, Kang Sun, Yufa Anhui University Key Lab of Intelligent Computing Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781665400541

In this paper, a compact multiple-input multiple-output (MIMO) antenna with two notches for wireless UWB applications is presented. The size of the proposed antenna is small, only 20 × 20 mm2. The radiating element of the antenna is a rectangular patch with a chamfered corner, and the inverted U-shaped slit on the patch is used to create the notches at wireless local area network and the downlink X-band of satellite communication. The isolation of more than 15 dB is achieved over the entire working frequency band (3.04-12.36 GHz). © 2019 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping

arXiv

引用

arXiv 2022年

作者： Xu, Jilan Hou, Junlin Zhang, Yuejie Feng, Rui Zhao, Rui-Wei Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Academy for Engineer and Technology Fudan University China Shanghai University of Finance and Economics China Deakin University Australia

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the activation values of the integral object regions. To this end, we introduce class-specific foreground and background context embeddings as cluster centroids. A CAM-guided momentum preservation strategy is developed to learn the context embeddings during training. At the inference stage, the re-activation mapping is formulated as a parameter estimation problem under Gaussian Mixture Model, which can be solved by deriving an unsupervised Expectation-Maximization based soft-clustering algorithm. By simply integrating CREAM into various WSOL approaches, our method significantly improves their performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and OpenImages benchmark datasets. Code will be available at https://***/Jazzcharles/CREAM. © 2022, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

arXiv

引用

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Simulation of Dual-Layer Metallic Nanowire Grids Broadband Polarizers Using the Finite-Difference Frequency-Domain Method 5

Simulation of Dual-Layer Metallic Nanowire Grids Broadband P...

引用

5th IEEE International Conference on Computational Electromagnetics, ICCEM 2019

作者： Wu, Gang Wu, Bo Huang, Zhixiang Key Laboratory of Intelligent Computing Signal Processing Anhui University Hefei China

ISBN: (纸本)9781538671115

We develop the broadband polarizers functioning in an extremely wide wavelength range from 0.3 to 5 μ m based on structural design and numerical simulation. The finite-difference frequency-domain (FDFD) method is a powerful and simple method for analyzing the electromagnetic structures. We propose a broadband polarizer using dual-layer metallic nanowire grids on a substrate, reflectance and transmittance are simulated by the FDFD method including normal incidence and oblique incidence. © 2019 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Staggered Grid Scheme for the FFT-Based Methods

引用

Chinese Journal of Electronics 2019年第5期28卷 1066-1072页

作者： XIE Jiaye KONG Weibin PANG Lili SONG Weiju HUANG Zhixiang WU Xianliang Industrial Center Nanjing Institute of Technology State Key Laboratory of Millimeter Waves College of Information Engineering Yancheng Institute of Technology Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University

A staggered grid scheme is proposed to reduce both the total memory requirement and the CPU time of generating the corrected near matrix in the FFTbased methods. Two sets of Cartesian grids are used to project the source points and the field points, *** proposed method does not lower the efficiency of computing far matrix-vector products, compared with the traditional uniform Cartesian grid scheme. Some numerical experiments are provided to demonstrate both the correctness and the efficiency of the proposed method.

关键词： Green’s function Singularity RFG-FFT Staggered grid scheme Corrected near matrix

来源：评论

学校读者我要写书评

暂无评论

Interactive Prototype Learning and Self-Learning for Few-Shot Medical Image Segmentation

SSRN

引用

SSRN 2024年

作者： Song, Yuhui Xu, Chenchu Wang, Boyan Du, Xiuquan Chen, Jie Zhang, Yanping Li, Shuo School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230051 China Department of Computer Science and Technology Tsinghua University Beijing100084 China School of Engineering Case Western Reserve University Cleveland44106 United States

Few-shot learning alleviates the heavy dependence of medical image segmentation tasks on large-scale labeled data, but it shows a strong performance gap when dealing with new targets and new tasks compared with traditional deep learning. Existing few-shot medical image segmentation models mainly realize segmentation by learning the semantic class knowledge of a few known (support) samples and extending it to unknown (query) samples. However, the neglect of the differences between known and unknown samples leads to a certain deviation in the transfer of class knowledge, and the trained model tends to overfit the class knowledge of training classes, which greatly reduces the segmentation and generalization performance of few-shot model. In this work, we propose an interactive prototype learning and self-learning network to alleviate the above problems. Specifically, we propose an interactive prototype learning network to promote feature consistency between support images and query images to improve the accuracy of prototype metric learning. In addition, to avoid overfitting the training class knowledge and reduce the over-dependence of query segmentation on the class knowledge, we introduce a query features-guided self-learning network to achieve the finer segmentation of query images through its rich feature information. Our model obtained the competitive segmentation results on three multi-organ and multi-modal public datasets that show a substantial improvement in generalization ability. © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

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：