检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zhang, Xiang Li, Xuanya Hu, Kai Gao, Xieping Xiangtan University Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan411105 China Baidu Inc. Beijing100085 China Key Laboratory of Medical Imaging and Artifical Intelligence of Hunan Province Xiangnan University Chenzhou423000 China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China

ISBN: (纸本)9781665401265

In this paper, we propose a novel convolutional neural network based on boundary-guided and region-aware (BGRA-Net) for breast tumor segmentation in ultrasound images. In particular, in the encoding stage, we propose a boundary-guided module (BGM) to guide the learning of boundary features in the decoding stage by explicitly strengthening the extracted boundary information. Meanwhile, in the decoding stage, we propose a region-aware module (RAM) to integrate different levels of detailed and semantic features to improve the comprehensive representation of tumor regional features. Besides, a scale-adaptive module (SAM) is further proposed to capture the characteristics of tumors with different sizes between the encoding and decoding stages. To evaluate the effectiveness of our BGRA-Net, we conduct extensive experiments on the UDIAT dataset and compare it with eight state-of-the-art methods. The experimental results show that our BGRA-Net outperforms the state-of-the-art methods and can achieve accurate segmentation of breast tumors with ambiguous boundaries. © 2021 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Recursive Constrained Sine Second-Order Error Promoting Adaptive Algorithm

TechRxiv

引用

TechRxiv 2023年

作者： Li, Yingsong Chen, Yong Miao, Yongchun Zakharov, Yuriy Huang, Zhixiang The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei230601 China The School of Physics Engineering and Technology University of York YorkYO10 5DD United Kingdom

This brief proposes a recursive constrained sine second-order error promoting adaptive (RCSSOEPA) algorithm. Compared with classical recursive method, the RCSSOEPA algorithm can achieve better steady state performance in impulsive noise. In general, the sine second-order error (SSOE) is constructed to devise a new recursive constrained adaptive-filtering within the least-squares framework for solving linear constrained optimization problems. The mean-square (MS) stability of the RCSSOEPA and its theoretical instantaneous MS deviation under Gaussian and non Gaussian noise are analyzed, numerically investigated and discussed in detail. Simulated results are reported to give a comfirmation of the theoretical analysis, and show that the RCSSOEPA outperforms recent developed constrained adaptive filtering algorithms in the estimation misalignment and when used for system identification under impulsive-noise. © 2023, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification 39

Bidirectional Logits Tree: Pursuing Granularity Reconcilemen...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lu, Zhiguang Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

ISBN: (纸本)157735897X

This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

arXiv

引用

arXiv 2025年

作者： Xiang, Wenzhao Liu, Chang Yu, Hongyang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Peng Cheng Laboratory China University of Chinese Academy of Sciences China Department of Electronic Engineering Shanghai Jiao Tong University China

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

SafeCFG: Redirecting Harmful Classifier-Free Guidance for Safe Generation

arXiv

引用

arXiv 2024年

作者： Pan, Jiadong Gao, Hongcheng Li, Liang Zha, Zheng-Jun Huang, Qingming Luo, Jiebo Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China University of Chinese Academy of Sciences China University of Science and Technology of China China University of Rochester United States

Diffusion models (DMs) have demonstrated exceptional performance in text-to-image (T2I) tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), the quality of images generated by DMs is improved. However, DMs can generate more harmful images by maliciously guiding the image generation process through CFG. Some safe guidance methods aim to mitigate the risk of generating harmful images but often reduce the quality of clean image generation. To address this issue, we introduce the Harmful Guidance Redirector (HGR), which redirects harmful CFG direction while preserving clean CFG direction during image generation, transforming CFG into SafeCFG and achieving high safety and quality generation. We train HGR to redirect multiple harmful CFG directions simultaneously, demonstrating its ability to eliminate various harmful elements while preserving high-quality generation. Additionally, we find that HGR can detect image harmfulness, allowing for unsupervised fine-tuning of safe diffusion models without pre-defined clean or harmful labels. Experimental results show that by incorporating HGR, images generated by diffusion models achieve both high quality and strong safety, and safe DMs trained through unsupervised methods according to the harmfulness detected by HGR also exhibit good safety performance. The codes will be publicly available. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Memory-Augmented Transformer for Efficient End-to-End Video Grounding

Memory-Augmented Transformer for Efficient End-to-End Video ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuanwu Xu Mohan Chen Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics School of Information Technology Deakin University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Video grounding aims to localize a specific segment corresponding to a text query in an untrimmed video. Due to the tremendous computational cost required to process the video frames, the de facto paradigm of video grounding is to extract video features using pretrained video encoders. The parameters of the video encoders are fixed during training, which limits the performance of the localization model. To solve this problem, we propose a Memory-Augmented Transformer (MAT) model. Specifically, each video is split into non-overlapping clips, and our MAT processes videos in a clip-by-clip manner while caching video features into FIFO cached memory queues. By enabling early return, our MAT outperforms previous methods with only less than 60% frames seen. Extensive experimental results on three public benchmark datasets demonstrate that our MAT can achieve competitive performance while being much more efficient than currently prevailing two-stage methods. Code is available at https://***/xuyw1997/MAT.

关键词： Training Location awareness Codes Grounding Computational modeling Streaming media Predictive models

来源：评论

学校读者我要写书评

暂无评论

Design of Low-profile Broadband Circularly Polarized Metasurface Antenna Based on CPW Feed

Design of Low-profile Broadband Circularly Polarized Metasur...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yue Ma Bo Wu Changqing Liu Xianliang Wu Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9781665409889

This paper presents a low-profile broadband circularly polarized metasurface antenna based on CPW feed. The antenna works in the 3.9-8.5 GHz frequency band, the metasurface consists of $5\times 5$ square cut corner metal patches printed on the upper surface of the dielectric substrate. In order to make the metasurface have the same characteristics for X polarization and Y polarization, the structure is designed to be symmetric in the slant -45° direction, and the size of the cut angle is changed to generate a circularly polarized wave. According to the phase of the incident wave at different positions on the metasurface, the distance between the 9 radiation elements at the center of the metasurface is 0.3 mm, and the distance between the 16 radiation elements in the outermost layer is 0.4 mm, so as to obtain a more suitable phase compensation. The lower surface of the dielectric substrate adopts a CPW coupling aperture structure as a feed source, and the coupling aperture adopts a stair-shape structure to achieve broadband impedance matching, and the stair-shape aperture is attached to the end of the CPW. The proposed antenna has a simple structure and a low profile, which can be realized by a single-layer printed circuit board (PCB) substrate. To verify the simulation results, a model antenna with an overall size of 0.9$\lambda_{0}$× 0.9$\lambda_{0}$× 0.06$\lambda_{0}$, where $\lambda_{0}$ is the free-space wavelength at 5 GHz, is fabricated. The measurement results show that the -10dB return loss bandwidth reaches 72.8%, the circular polarization axis ratio (AR) is less than 3 dB with a bandwidth of 21.6%, and the highest gain reaches 8.34 dBi, which is almost consistent with the simulation results.

关键词： Antenna measurements Polarization Bandwidth Apertures Metasurfaces Antenna feeds Loss measurement

来源：评论

学校读者我要写书评

暂无评论

Transient Electro-thermal and Bandgap Narrowing Analysis of the bipolar transistor

Transient Electro-thermal and Bandgap Narrowing Analysis of ...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Hui Xiao Xingang Ren Yeqiang Yan Zhixiang Huang Xianliang Wu Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Chizhou Anhui Province China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

Given the bandgap narrowing (BGN) effect caused by heavy doping of the bipolar transistor and the self-heating effect (SHE) in the practical work environment, a transient electro-thermal and bandgap narrowing model is proposed in this paper, which is based on the Slotboom model and the modification of the drift-diffusion equation based on semiconductor equations and the heat conduction equation. The transient characteristics of the bipolar transistor in amplification mode are simulated using the differential method, and the results show that the terminal current of the bipolar transistor decreases after considering the SHE and the BGN effect. The model developed and the results obtained in this work can provide some reference significance for the optimization of the amplification characteristics of the bipolar transistor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transient Electro-thermal Analysis of the Bipolar Transistor

Transient Electro-thermal Analysis of the Bipolar Transistor

引用

International Review of Progress in Applied Computational Electromagnetics (ACES)

作者： Hui Xiao Xingang Ren Yeqiang Yan Junjie Si Xueyuan Cai Bo Wu Zhixiang Huang Xianliang Wu Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Chizhou Anhui Province China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

This paper describes the transient electro-thermal properties of the bipolar transistor by a two-dimensional transient electro-thermal simulation, in which model the coupled heat conduction equation and drift-diffusion equations are solved. The backward difference scheme with the second-order accuracy was used to discretize the time derivative. The increment of bipolar transistor temperature will affect the drift and diffusion of carriers and thus its electrical characteristics. Through the transient study of electro-thermal characteristics of the bipolar transistor, the influence of the self-heating effect on bipolar transistor characteristic has considered in amplification mode. The developed model and results obtained in this work can be used to optimize the thermal design of bipolar transistor.

关键词： Performance evaluation Heating systems Bipolar transistors Temperature Electric variables Computational electromagnetics Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Design of Miniaturized UWB Antenna with Rectangular Slot

Design of Miniaturized UWB Antenna with Rectangular Slot

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Minquan Li Ziyun Tu Ran Zhao Guangxiu Zhao Yajing Yan Xiaming Mo Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (纸本)9781665409889

A miniaturized ultra-wideband (UWB) antenna with excellent performance is designed in this paper. The antenna is based on hexagonal metal patch, and a circular arc structure is added on the top of the antenna, which widens the effective frequency band of the antenna. The current path is changed by opening rectangular slots on the surface and bottom of the antenna, which greatly improves the in-band characteristics of the antenna. The size of the antenna is 29mm × 31 mm × 1.5 mm after continuous optimization with HFSS. The final test results show that the impedance bandwidth of the antenna less than -10 dB is 3.5 GHz ∼ 19.5 GHz, and it has good radiation characteristics in this frequency band range. The antenna achieves the design goal of miniaturization and UWB, and has a good application prospect in communication system.

关键词： Surface impedance Slot antennas Simulation Ultra wideband communication Metals Bandwidth Ultra wideband antennas

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：