检索结果-内蒙古大学图书馆

Boosting polyp screening with improved point-teacher weakly semi-supervised

computers in Biology and Medicine 2025年 191卷 109998-109998页

作者： Du, Xiuquan Zhang, Xuejun Chen, Jiajia Li, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Department of Neurology Shuyang Affiliated Hospital of Nanjing University of Traditional Chinese Medicine Suqian China School of Computer Science and Technology Anhui University Hefei China

Polyps, like a silent time bomb in the gut, are always lurking and can explode into deadly colorectal cancer at any time. Many methods are attempted to maximize the early detection of colon polyps by screening, however, there are still face some challenges: (i) the scarcity of per-pixel annotation data and clinical features such as the blurred boundary and low contrast of polyps result in poor performance. (ii) existing weakly semi-supervised methods directly using pseudo-labels to supervise student tend to ignore the value brought by intermediate features in the teacher. To adapt the point-prompt teacher model to the challenging scenarios of complex medical images and limited annotation data, we creatively leverage the diverse inductive biases of CNN and Transformer to extract robust and complementary representation of polyp features (boundary and context). At the same time, a novel designed teacher–student intermediate feature distillation method is introduced rather than just using pseudo-labels to guide student learning. Comprehensive experiments demonstrate that our proposed method effectively handles scenarios with limited annotations and exhibits good segmentation performance. All code is available at https://***/dxqllp/WSS-Polyp. © 2025 Elsevier Ltd

关键词： Weakly semi-supervised Medical image segmentation Boundary extraction Feature distillation

来源：评论

学校读者我要写书评

暂无评论

An Optimal Sequence Reconstruction Algorithm for Reed-Solomon Codes

arXiv

引用

arXiv 2024年

作者： Singhvi, Shubhransh Con, Roni Kiah, Han Mao Yaakobi, Eitan Signal Processing & Communications Research Center IIIT Hyderabad India Department of Computer Science Technion—Israel Institute of Technology Haifa3200003 Israel School of Physical and Mathematical Sciences Nanyang Technological University Singapore

The sequence reconstruction problem, introduced by Levenshtein in 2001, considers a scenario where the sender transmits a codeword from some codebook, and the receiver obtains N noisy outputs of the codeword. We study the problem of efficient reconstruction using N outputs that are corrupted by substitutions. Specifically, for the ubiquitous Reed-Solomon codes, we adapt the Koetter-Vardy soft-decoding algorithm, presenting a reconstruction algorithm capable of correcting beyond Johnson radius. Furthermore, the algorithm uses O(nN) field operations, where n is the codeword length. Copyright © 2024, The Authors. All rights reserved.

关键词： Reed-Solomon codes

来源：评论

学校读者我要写书评

暂无评论

Enhanced Color Palette Modeling For Lossless Screen Content Compression

Enhanced Color Palette Modeling For Lossless Screen Content ...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Hannah Och Shabhrish Reddy Uddehal Tilo Strutz André Kaup Multimedia Communications and Signal Processing Friedrich-Alexander Universität Erlangen-Nürnberg (FAU) Erlangen Germany Department of Electrical Engineering and Computer Science Coburg University of Applied Sciences and Arts Coburg Germany

Soft context formation is a lossless image coding method for screen content. It encodes images pixel by pixel via arithmetic coding by collecting statistics for probability distribution estimation. Its main pipeline includes three stages, namely a context model based stage, a color palette stage and a residual coding stage. Each subsequent stage is only employed if the previous stage can not be applied since necessary statistics, e.g. colors or contexts, have not been learned yet. We propose the following enhancements: First, information from previous stages is used to remove redundant color palette entries and prediction errors in subsequent stages. Additionally, implicitly known stage decision signals are no longer explicitly transmitted. These enhancements lead to an average bit rate decrease of 1.07% on the evaluated data. Compared to VVC and HEVC, the proposed method needs roughly 0.44 and 0.17 bits per pixel less on average for 24-bit screen content images, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection and Characterization of Human Veins Using Infra-Red Image processing

引用

Journal of computer and Communications 2024年第9期12卷 141-159页

作者： Jean Ndoumbe Brice Ekobo Akoa Gaelle Patricia Talotsing Frederic Franck Kounga Samuel Kaissassou Bertin Chouanmo Njo Laboratory of Computer Engineering Data Science and Artificial Intelligence Department of Computer & Telecommunications Engineering National Higher Polytechnic School Douala Cameroon Laboratory of Electrical Engineering Mechatronics and Signal Processing Department of Electrical & Telecommunications Engineering National Advanced School of Engineering Yaound Cameroon Mobile Computing and Networking Research Laboratory Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada DigiPlus SARL Bonamoussadi Douala Cameroon

The detection and characterization of human veins using infrared (IR) image processing have gained significant attention due to its potential applications in biometric identification, medical diagnostics, and vein-based authentication systems. This paper presents a low-cost approach for automatic detection and characterization of human veins from IR images. The proposed method uses image processing techniques including segmentation, feature extraction, and, pattern recognition algorithms. Initially, the IR images are preprocessed to enhance vein structures and reduce noise. Subsequently, a CLAHE algorithm is employed to extract vein regions based on their unique IR absorption properties. Features such as vein thickness, orientation, and branching patterns are extracted using mathematical morphology and directional filters. Finally, a classification framework is implemented to categorize veins and distinguish them from surrounding tissues or artifacts. A setup based on Raspberry Pi was used. Experimental results of IR images demonstrate the effectiveness and robustness of the proposed approach in accurately detecting and characterizing human. The developed system shows promising for integration into applications requiring reliable and secure identification based on vein patterns. Our work provides an effective and low-cost solution for nursing staff in low and middle-income countries to perform a safe and accurate venipuncture.

关键词： Vein Detection Blood Radiation Infrared Image CLAHE Algorithm Raspberry Pi

来源：评论

学校读者我要写书评

暂无评论

Improved Screen Content Coding in VVC Using Soft Context Formation

Improved Screen Content Coding in VVC Using Soft Context For...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

Screen content images typically contain a mix of natural and synthetic image parts. Synthetic sections usually are comprised of uniformly colored areas and repeating colors and patterns. In the VVC standard, these properties are exploited using Intra Block Copy and Palette Mode. In this paper, we show that pixel-wise lossless coding can outperform lossy VVC coding in such areas. We propose an enhanced VVC coding approach for screen content images using the principle of soft context formation. First, the image is separated into two layers in a block-wise manner using a learning-based method with four block features. Synthetic image parts are coded losslessly using soft context formation, the rest with VVC. We modify the available soft context formation coder to incorporate information gained by the decoded VVC layer for improved coding efficiency. Using this approach, we achieve Bjontegaard-Delta-rate gains of 4.98% on the evaluated data sets compared to VVC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PARTICLE FLOW GAUSSIAN SUM PARTICLE FILTER

arXiv

引用

arXiv 2022年

作者： Comandur, Karthik Li, Yunpeng Nannuru, Santosh Signal Processing and Communication Research Centre IIIT Hyderabad India Department of Computer Science University of Surrey United Kingdom

The particle flow Gaussian particle filter (PFGPF) uses an invertible particle flow to generate a proposal density. It approximates the predictive and posterior distributions as Gaussian densities. In this paper, we use a bank of PFGPF filters to construct a Particle flow Gaussian sum particle filter (PFGSPF), which approximates the prediction and posterior as Gaussian mixture model. This approximation is useful in complex estimation problems where a single Gaussian approximation is inadequate. We compare the performance of this proposed filter with the PFGPF and others in challenging numerical simulations. © 2022, CC BY-NC-ND.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Differentiable Bootstrap Particle Filters for Regime-Switching Models

Differentiable Bootstrap Particle Filters for Regime-Switchi...

引用

IEEE/SP Workshop on Statistical signal processing (SSP)

作者： Wenhan Li Xiongjie Chen Wenwu Wang Víctor Elvira Yunpeng Li Department of Computer Science University of Surrey Guildford UK Centre for Vision Speech and Signal Processing University of Surrey Guildford UK School of Mathematics University of Edinburgh Edinburgh UK

Differentiable particle filters are an emerging class of particle filtering methods that use neural networks to construct and learn parametric state-space models. In real-world applications, both the state dynamics and measurements can switch between a set of candidate models. For instance, in target tracking, vehicles can idle, move through traffic, or cruise on motorways, and measurements are collected in different geographical or weather conditions. This paper proposes a new differentiable particle filter for regime-switching state-space models. The method can learn a set of unknown candidate dynamic and measurement models and track the state posteriors. We evaluate the performance of the novel algorithm in relevant models, showing its great performance compared to other competitive algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speaker Recognition Based on Pre-Trained Model and Deep Clustering

Speaker Recognition Based on Pre-Trained Model and Deep Clus...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liang He Zhida Song Shuanghong Liu Mengqi Niu Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University Urumqi China School of Intelligence Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

In this paper, we propose a novel loss by integrating a deep clustering (DC) loss at the frame-level and a speaker recognition loss at the segment-level into a single network without additional data requirements and exhaustive computation. The DC loss implicitly generates soft pseudo-phoneme labels for each frame-level feature, which facilitates extracting more discriminant speaker representation by suppressing phonetic content information. We study the DC loss not only on the acoustic feature, but also on the features extracted by the pre-trained models, such as wav2vec 2.0, HuBERT and WavLM. Experimental results on the VoxCeleb dataset shows that the overall system performance based on the pre-trained model features are better than the one on the acoustic feature. The proposed loss is significantly effective for systems on the acoustic feature and has a marginal improvement for systems on the pre-trained model feature.

关键词： Training Costs Computational modeling System performance Phonetics Multimedia databases Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Improved IHS Image Fusion Algorithm using Medoid Intensity Match and Bilateral Filter

An Improved IHS Image Fusion Algorithm using Medoid Intensit...

引用

2021 IEEE India Geoscience and Remote Sensing Symposium, InGARSS 2021

作者： Tiwari, Manan Manoj Misra, Indranil Moorthi, S. Manthira Dhar, Debajyoti Bennett University Computer Science Department Uttar Pradesh Greater Noida India ISRO Signal and Image Processing Group Space Applications Centre Gujarat Ahmedabad India

ISBN: (纸本)9781665442497

Image fusion is a productive way to combine multi-sensor images and extract maximum information from enhance remote sensing data. The paper describes a novel methodology to improve IHS image fusion algorithm by medoid intensity computation from multispectral images and suppress noise of panchromatic image using bilateral filter. Medoid provides an optimal representation of multispectral images and act as an intensity component in IHS color space. Bilateral filter preserves the edge information of high resolution data while reduce the noise in homogenous regions. Improved IHS image fusion algorithm by amalgamation of medoid intensity and bilateral filter found to be an effective technique to generate fused images. The technique developed is evaluated with Cartosat-1 panchromatic and Resourcesat-2 multispectral closest acquisition images. The datasets are geometrically transformed and co-registered to make it eligible for image fusion exercises. The visual assessment confirms improved IHS better retain the spatial details while preserving the spectral characteristics. Improved IHS is compared with state-of-the-art component substitution image fusion techniques and found to be perform better in almost all the standard metrics. © 2021 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Ver...

引用

International Symposium on Chinese Spoken Language processing

作者： Shuanghong Liu Zhida Song Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Due to its superior performance and fewer parameters, CAM++ has become the state-of-the-art model for speaker verification tasks. This model uses 2D convolutional blocks to extract front-end features, which are then fed into a densely connected time-delay neural network backbone to extract deep features. However, the simple stacking of 2D convolutions may lead to the generation of a significant amount of redundant features, which is detrimental to efficient feature extraction. Furthermore, although CAM++ already has a relatively small number of parameters, there is still room for further optimization. To address these issues, this paper first employs depthwise separable convolutions to replace the dilated convolutions in the back-end network of CAM++, making the model more lightweight. Next, we introduce spatial and channel reconstruction convolution (SCConv) in the ResBlock module of CAM++ to reduce redundant features and optimize the feature extraction process. Finally, after SCConv, we apply squeeze and excitation attention mechanism to model the interdependencies between channels and recalibrate each channel, further enhancing the model's representational capacity. We name the resulting model LE-CAM++. Our proposed model achieves an EER of 0.686 and a minDCF of 0.084 on the VoxCeleb1–O dataset. Compared to the baseline model CAM ++, the EER is reduced by 11%, and the minDCF is reduced by 28%. Additionally, the model parameters are reduced by 8%.

关键词： Attention mechanisms Stacking Neural networks Feature extraction Optimization

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：