检索结果-内蒙古大学图书馆

17th IEEE International Conference on e-Business engineering, ICEBE 2021

作者： Hao, Yun Huang, Xiangkang Huang, Huichou Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Lab Guangzhou China University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9781665444187

The speech dialogue system has gradually been widely used in daily life. Users can consult and communicate with the system through natural language. However, in practical applications, third-person background sounds and background noise interference in real dialogue scenes will be encountered. The uncertainty and complexity of these background sounds will have a bad impact on the recognition of the system. A good speech enhancement module can help us to separate the target speaker from the original speech. Recently, a solution called SpEx+ was proposed from the time domain, but SpEx+ needs a reference speech to assist in training. This reference speech may have noise in actual applications that will affect performance. Therefore, we propose a Denoi-SpEx+ model. Before the reference speech is input to the network, a speech denoising network is added, so that the quality of speech separation in practical applications can be guaranteed. Experiments show that our model can significantly improve the performance of speech separation model of noisy reference speech. © 2021 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Relation-Based Multi-Teacher Knowledge Distillation

Relation-Based Multi-Teacher Knowledge Distillation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yutian Wang Yi Xu School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu China Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traditional knowledge distillation adopts one teacher model to instruct the training of a lightweight student model. To improve the performance of knowledge distillation, multi-teacher knowledge distillation utilizing multi-party knowledge to guide model learning was proposed. However, existing methods mainly use the summation-result of teacher models of a single sample to integrate multi-party knowledge directly, ignoring the relation knowledge among samples. In this paper, we propose a novel multi-teacher knowledge distillation method, which utilizes the data relation knowledge to allocate weights for teachers adaptively. To obtain the data relation knowledge, we design output-based strategy and feature-based strategy, which would help to allocate more weight for the teacher who has better learned the data relation knowledge. Extensive experiments have demonstrated the performance and efficiency of our proposed multi-teacher knowledge distillation method.

关键词： Training Adaptation models Neural networks

来源：评论

学校读者我要写书评

暂无评论

multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information

arXiv

引用

arXiv 2024年

作者： Zhu, Hongjun Huang, Jiaohang Chen, Kuo Ying, Xuehui Qian, Ying School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Engineering Research Center of Software Quality Assurance Testing and Assessment Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Brain Tumor Segmentation (BraTS) plays a critical role in clinical diagnosis, treatment planning, and monitoring the progression of brain tumors. However, due to the variability in tumor appearance, size, and intensity across different MRI modalities, automated segmentation remains a challenging task. In this study, we propose a novel Transformer-based framework, multiPI-TransBTS, which integrates multi-physical information to enhance segmentation accuracy. The model leverages spatial information, semantic information, and multi-modal imaging data, addressing the inherent heterogeneity in brain tumor characteristics. The multiPI-TransBTS framework consists of an encoder, an Adaptive Feature Fusion (AFF) module, and a multi-source, multi-scale feature decoder. The encoder incorporates a multi-branch architecture to separately extract modality-specific features from different MRI sequences. The AFF module fuses information from multiple sources using channel-wise and element-wise attention, ensuring effective feature recalibration. The decoder combines both common and task-specific features through a Task-Specific Feature Introduction (TSFI) strategy, producing accurate segmentation outputs for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET) regions. Comprehensive evaluations on the BraTS2019 and BraTS2020 datasets demonstrate the superiority of multiPI-TransBTS over the state-of-the-art methods. The model consistently achieves better Dice coefficients, Hausdorff distances, and Sensitivity scores, highlighting its effectiveness in addressing the BraTS challenges. Our results also indicate the need for further exploration of the balance between precision and recall in the ET segmentation task. The proposed framework represents a significant advancement in BraTS, with potential implications for improving clinical outcomes for brain tumor patients. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Xin Xu, Feng Tao, Feifei Tong, Yao Lyu, Xin Zhong, Jianyi Kaup, André College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9798350368741

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study. © 2025 IEEE.

关键词： frequency transformer remote sensing images Semantic segmentation spectrum enhancement

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Low-Dose CT Reconstruction Using dataset-Free Learning

SSRN

引用

SSRN 2024年

作者： Wang, Feng Wang, Renfang Yang, Bo Qiu, Hong College of Big Data and Software Engineering Zhejiang Wanli University Zhejiang Ningbo315100 China Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Zhejiang Hangzhou310027 China

Low-Dose computer tomography (LDCT) is an ideal alternative to reduce radiation risk in clinical applications. Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging. In this paper, we propose an unsupervised and training data-free learning reconstruction method for LDCT imaging that avoids the requirement for training data. The proposed method is a post-processing technique that aims to enhance the initial low-quality reconstruction results, and it reconstructs the high-quality images by neural work training that minimizes the l-norm distance between the CT measurements and their corresponding simulated sinogram data, as well as the total variation (TV) value of the reconstructed image. Moreover, the proposed method does not require to set the weights for both the data fidelity term and the plenty term. Experimental results on the AAPM challenge data and LoDoPab-CT data demonstrate that the proposed method is able to effectively suppress the noise and preserve the tiny structures. And these results also shows the proposed method's low computational cost and rapid convergence. The source code is available at https://***/linfengyu77/IRLDCT. © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware contrastive learning for selective classification 24

Confidence-aware contrastive learning for selective classifi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yu-Chang Wu Shen-Huan Lyu Haopu Shang Xiangyu Wang Chao Qian National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China and National Key Laboratory for Novel Software Technology Nanjing University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relep: Region and Edge Synergetic Level Set Model Based on Edge-Enhanced Entropy and Variable Exponential P-Laplace Equation

SSRN

引用

SSRN 2023年

作者： Wu, Jiangfeng Zhou, Zhiheng Zhou, Wenlue Tao, Xiyuan Deng, Ming School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou China

Image segmentation under conditions such as noise and intensity inhomogeneity poses a significant challenge for models. Hybrid level set approaches integrating area and edge information show promise in addressing these challenges. In this study, we propose a novel hybrid level set model, called region and edge synergetic level set model based on edge-enhanced entropy and variable exponential p-Laplace equation (RELEP), which is based on an edge-enhanced entropy and a variable exponential p-Laplace equation. Firstly, a new probability distribution is defined to enhance the edge extraction ability of image entropy in the presence of image intensity inhomogeneity and noise, termed as edge-enhanced entropy. The feature map obtained after edge-enhanced entropy processing is then used to co-fit the energy function with the original map to form the region term. Furthermore, the incorporation of edge-enhanced entropy into the p-Laplace equation leads to the formation of a variable exponential p-Laplace equation edge term. This integration facilitates the acquisition of precise and smooth boundaries, while simultaneously bolstering the robustness of the model. Finally, by incorporating the region term and edge term into the variational level set framework, the RELEP model is proposed. Experimental results on both synthetic and natural images demonstrate that the proposed RELEP model outperforms several representative and state-of-the-art models in terms of segmentation performance. © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction of 3D Visualized Images based on Multiscale Measurement

Feature Extraction of 3D Visualized Images based on Multisca...

引用

2023年第三届创新人才培养与可持续发展国际学术会议

作者： Haixiao Gong Siqi Zhou School of Data Science & Software Engineering Wuzhou University Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University

3D visualization image can improve the recognition ability of massive images, and extracting the features of 3D visualization image can further enhance the image processing ability. Firstly, the 3D visualization image is segmented by multi-scale, and then the basic parameters are obtained. Finally, the 3D visualization image feature is extracted by region growing method. The method of feature extraction designed by realizing the discovery has higher accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoupled Prototype Learning for Reliable Test-Time Adaptation

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui South China University of Technology School of Electronic and Information Engineering 381 Wushan Road Tianhe District Guangzhou510000 China Pazhou Lab Guangzhou510330 China South China University of Technology School of Future Technology 381 Wushan Road Tianhe District Guangzhou510000 China South China University of Technology School of Software Engineering Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL's robustness for the small batch sizes often encountered in TTA. We update each class's pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. © 1999-2012 IEEE.

关键词： Benchmarking

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：