检索结果-内蒙古大学图书馆

Aortic KD former: aortic multiclass segmentation using SegFormer via knowledge distillation

Machine Learning: science and technology 2025年第2期6卷

作者： Mohamed Soliman, Nancy Awadalla, Medhat Elhelw, Mohamed Elattar, Mustafa Medical Imaging and Image Processing Research Group Center for Informatics Science Nile University Giza Egypt Department of Computers and Systems Helwan University Helwan Cairo Egypt School of Information Technology and Computer Science Nile University Giza Egypt

In this paper, we investigate the effectiveness of knowledge distillation for semantic segmentation of aortic structures using deep learning models. We employ SegFormer B5 as the teacher model and SegFormer B0 as the student model. Knowledge distillation is applied through three methods: output-based distillation, inner feature maps-based distillation, and integrated distillation, which combines both logits and feature maps. Our results show that while the student model (SegFormer B0) has significantly fewer parameters (3,715,686) compared to the teacher model (SegFormer B5) with 84,597,958 parameters, it achieves performance closely approaching that of the teacher. Among the evaluated techniques, inner feature map distillation yields the best performance, with a mean IoU of 0.9994, a mean Dice score of 0.9549, and a loss of 0.0020, demonstrating its superior capability in transferring knowledge effectively. The study highlights the potential of inner feature map distillation as the most effective method for achieving high performance with reduced model complexity. © 2025 The Author(s). Published by IOP Publishing Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards realistic evaluation of cultural value alignment in large language models: Diversity enhancement for survey response simulation

引用

Information processing and Management 2025年第4期62卷

作者： Liu, Haijiang Cao, Yong Wu, Xun Qiu, Chen Gu, Jinguang Liu, Maofu Hershcovich, Daniel School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China Tübingen AI Center University of Tübingen Tübingen72074 Germany Division of Social Science The Hong Kong University of Science and Technology 511455 Hong Kong Department of Computer Science University of Copenhagen Copenhagen Denmark

Assessing Large Language Models (LLMs) alignment with human values has been a high priority in natural language processing. These models, praised as reservoirs of collective human knowledge, provoke an important question: Do they genuinely reflect the value preferences embraced by different cultures? We measure value alignment by simulating sociological surveys and comparing the distribution of preferences from model responses to human references. We introduce a diversity-enhancement framework featuring a novel memory simulation mechanism, which enables the generation of model preference distributions and captures the diversity and uncertainty inherent in LLM behaviors through realistic survey experiments. To better understand the causes of misalignment, we have developed comprehensive evaluation metrics. Our analysis of multilingual survey data illustrates that our framework improves the reliability of cultural value alignment assessments and captures the complexity of model responses across cultural contexts. Among the eleven models evaluated, the Mistral and Llama-3 series show superior alignment with cultural values, with Mistral-series models notably excelling in comprehending these values in both U.S. and Chinese contexts. © 2025 Elsevier Ltd

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

MN-Net: Speech Enhancement Network via Modeling the Noise

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 1208-1219页

作者： Ying Hu Qin Yang Wenbing Wei Li Lin Liang He Zhijian Ou Wenzhong Yang School of Computer Science and Technology Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Xinjiang Institute of Electronics Research Shares Company Ltd. Urumqi China Department of Electrical Engineering Tsinghua University Beijing China Beijing National Research Center for information Science and Technology Department of Electronics Tsinghua University Beijing China

Currently, deep learning-based speech enhancement methods generally focus on target speech extraction while neglecting modeling the other sound sources in the mixture. These methods still can't distinguish the target speech from the interference well. In this paper, we present a monaural speech enhancement network via Modeling the Noise (MN-Net), which includes a shared Encoder and three separate Decoders for parallel modeling the magnitude and phase spectrogram of target speech, and the complex spectrogram of noise. Specifically, we propose a Multi-Branch Feature Extractor (MBFE) module to capture the richer contextual information in mixture, and a Spatial Reconstruction Unit (SRU) to remove the redundancy from extracted features. We compared our proposed MN-Net with 18 classical speech enhancement methods on the VoiceBank+DEMAND dataset, and with 9 ones on DNS-Challenge dataset for denoising task, and with 7 ones on the WHAMR! dataset for simultaneous denoising & de-reverberation task. Our proposed MBFE module was applied to two classical speech enhancement methods, DB-AIAT and CMGAN, replacing their DenseBlocks module. The results demonstrate that applying the MBFE module can boost their performances while keeping smaller model size. A series of visualization analysis intuitively verify that modeling the noise can enable the network to distinguish the target speech from noise and other interference more accurately.

关键词： Noise Feature extraction Spectrogram Speech enhancement Decoding Kernel Transformers Noise reduction Data mining Training

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Local and Global Feature Fusion for Blind Quality Assessment of Enhanced Images

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Cao, Jingchao Zhang, Shuai Liu, Yutao Gao, Feng Gu, Ke Zhai, Guangtao Dong, Junyu Kwong, Sam Ocean University of China School of Computer Science and Technology Qingdao266100 China Beijing University of Technology Faculty of Information Technology Beijing100124 China Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai200240 China Lingnan University Department of Computing and Decision Science Hong Kong

Image enhancement plays a crucial role in computer vision by improving visual quality while minimizing distortion. Traditional methods enhance images through pixel value transformations, yet they often introduce new distortions. Recent advancements in deep learning-based techniques promise better results but challenge the preservation of image fidelity. Therefore, it is essential to evaluate the visual quality of enhanced images. However, existing quality assessment methods frequently encounter difficulties due to the unique distortions introduced by these enhancements, thereby restricting their effectiveness. To address these challenges, this paper proposes a novel blind image quality assessment (BIQA) method for enhanced natural images, termed multi-scale local feature fusion and global feature representation-based quality assessment (MLGQA). This model integrates three key components: a multi-scale Feature Attention Mechanism (FAM) for local feature extraction, a Local Feature Fusion (LFF) module for cross-scale feature synthesis, and a Global Feature Representation (GFR) module using Vision Transformers to capture global perceptual attributes. This synergistic framework effectively captures both fine-grained local distortions and broader global features that collectively define the visual quality of enhanced images. Furthermore, in the absence of a dedicated benchmark for enhanced natural images, we design the Natural Image Enhancement Database (NIED), a largescale dataset consisting of 8,581 original images and 102,972 enhanced natural images generated through a wide array of traditional and deep learning-based enhancement techniques. Extensive experiments on NIED demonstrate that the proposed MLGQA model significantly outperforms current state-of-the-art BIQA methods in terms of both prediction accuracy and robustness. © 1991-2012 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

DHAG-DTA: Dynamic Hierarchical Affinity Graph Model for Drug-Target Binding Affinity Prediction

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 697-709页

作者： Cheng Wang Yang Liu Shitao Song Kun Cao Xiaoyan Liu Gaurav Sharma Maozu Guo School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical Engineering Liaoning University of Technology Liaoning China Department of Electrical and Computer Engineering University of Rochester Rochester NY USA School of Electrical and Information Engineering Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

Computational methods for predicting drug-target binding affinity (DTA) are critical for large-scale screening of prospective therapeutic compounds during drug discovery. Deep neural networks (DNNs) have recently shown significant promise for DTA prediction. By leveraging available data for training, DNNs can expand the use of DTA prediction to situations where only sequence information is available for potential drug molecules and their targets, and there is no prior knowledge regarding the molecular geometric conformations. We propose DHAG-DTA, a general dynamic hierarchical affinity graph DNN approach, for DTA prediction using molecular sequence information and already known drug-target interactions. DHAG-DTA introduces a two-level hierarchical graph structure: at the upper level, interactions between drug and target molecules are represented via an affinity graph and at the lower level, embedded molecular graphs represent interactions within the individual molecules. This allows for integration of information from both inter and intra molecular interactions for DTA prediction, which has also been addressed in other recent independent work. The fundamental innovations introduced by DHAG-DTA include: (a) a single overall hierarchical graph that allows better assimilation of information during the learning process compared with loosely-coupled individual graphs, (b) dynamic determination of the affinity graph structure via the introduction of unlabeled edges and a maximum entropy criterion for active edge selection, (c) skip connections in the DNN for fusing intra and inter molecular information, and (d) fusion of both model-based and similarity-based feature embeddings to get robust embeddings of unseen molecules. Experimental results on two common benchmark datasets demonstrate that DHAG-DTA outperforms other existing models on multiple evaluation metrics, achieving state-of-the-art performance.

关键词： Drugs Predictive models Graph neural networks Artificial neural networks Biological system modeling Proteins Atoms Computational modeling Bioinformatics Entropy

来源：评论

学校读者我要写书评

暂无评论

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior

arXiv

引用

arXiv 2025年

作者： Li, Mingrui Liu, Shuhong Deng, Tianchen Wang, Hongyu the Department of Computer Science Dalian University of Technology Dalian China the Department of Mechano-informatics Information Science and Technology The University of Tokyo Tokyo Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education China

Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods. © 2025, CC BY.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 1440-1453页

作者： Saierdaer Yusuyin Te Ma Hao Huang Wenbo Zhao Zhijian Ou School of Computer Science and Technology Xinjiang University Urumqi China China Unicom (Guangdong) Industrial Internet Company Ltd Guangzhou China Speech Processing and Machine Intelligence (SPMI) Lab Department of Electronic Engineering Tsinghua University Beijing China

There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic supervision has been underappreciated so far for MCL-ASR, while conceptually it is more advantageous for information sharing between different languages. This paper explores the approach of pretraining with weakly phonetic supervision towards data-efficient MCL-ASR, which is called Whistle. We relax the requirement of gold-standard human-validated phonetic transcripts, and obtain International Phonetic Alphabet (IPA) based transcription by leveraging the LanguageNet grapheme-to-phoneme (G2P) models. We construct a common experimental setup based on the CommonVoice dataset, called CV-Lang10, with 10 seen languages and 2 unseen languages. A set of experiments are conducted on CV-Lang10 to compare, as fair as possible, the three approaches under the common setup for MCL-ASR. Experiments demonstrate the advantages of phoneme-based models (Whistle) for MCL-ASR, in terms of speech recognition for seen languages, crosslingual performance for unseen languages with different amounts of few-shot data, overcoming catastrophic forgetting, and training efficiency. It is found that when training data is more limited, phoneme supervision can achieve better results compared to subword supervision and self-supervision, thereby providing higher data-efficiency.

关键词： Phonetics Multilingual Speech recognition Training Hidden Markov models Data models Symbols Error analysis Pipelines Information sharing

来源：评论

学校读者我要写书评

暂无评论

BAST: Blockchain-Assisted Secure and Traceable Data Sharing Scheme for Vehicular Networks

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4664-4678页

作者： Liu, Xinzhong Cui, Jie Zhang, Jing Yin, Rongwang Zhong, Hong Wei, Lu Bolodurina, Irina He, Debiao Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Hefei University Department of Basic Experiment and Training Hefei230601 China Orenburg State University Faculty of Mathematics and Information Technologies Orenburg460018 Russia Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shanghai Key Laboratory of Privacy Preserving Computation MatrixElements Technologies Shanghai201204 China

In vehicular networks, caching service content on edge servers (ESs) is a widely accepted strategy for promptly responding to vehicle requests, reducing communication overhead, and improving service experience. However, implementing such an architecture requires addressing the challenges associated with ES response data reliability and communication security. In this study, to tackle the ES response data reliability issue, a blockchain-assisted threshold signature scheme for cache-based vehicular networks is proposed. The scheme utilizes a threshold mechanism to sign the data broadcast by the ES, incorporates blockchain to trace malicious signers, and avoids the shortcomings and limitations associated with idealized assumptions for the ES in existing data-sharing schemes. Moreover, considering the communication security and high-speed mobility of vehicles, using the non-interactive signatures of knowledge based on the Σ-protocol, a secure and efficient message authentication scheme for vehicles and ESs is provided. Through rigorous security proofs and comprehensive analyses, our scheme satisfies the communication security requirements of vehicular networks. By leveraging the JPBC library for performance analysis, the proposed scheme demonstrates advantages as concerns both computation and communication overheads compared to related schemes. Moreover, we implemented the proposed scheme on an Ethereum test network (i.e., Goerli) to validate its feasibility. © 2005-2012 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition 4th

SVFormer: A Direct Training Spiking Transformer for Efficie...

引用

4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024

作者： Yu, Liutao Huang, Liwei Zhou, Chenlin Zhang, Han Ma, Zhengyu Zhou, Huihui Tian, Yonghong AI Department Pengcheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China Faculty of Computing Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819640003

Video action recognition (VAR) plays crucial roles in various domains such as surveillance, healthcare, and industrial automation, making it highly significant for the society. Consequently, it has long been a research spot in the computer vision field. As artificial neural networks (ANNs) are flourishing, convolution neural networks (CNNs), including 2D-CNNs and 3D-CNNs, as well as variants of the vision transformer (ViT), have shown impressive performance on VAR. However, they usually demand huge computational cost due to the large data volume and heavy information redundancy introduced by the temporal dimension. To address this challenge, some researchers have turned to brain-inspired spiking neural networks (SNNs), such as recurrent SNNs and ANN-converted SNNs, leveraging their inherent temporal dynamics and energy efficiency. Yet, current SNNs for VAR also encounter limitations, such as nontrivial input preprocessing, intricate network construction/training, and the need for repetitive processing of the same video clip, hindering their practical deployment. In this study, we innovatively propose the directly trained SVFormer (Spiking Video transFormer) for VAR. SVFormer integrates local feature extraction, global self-attention, and the intrinsic dynamics, sparsity, and spike-driven nature of SNNs, to efficiently and effectively extract spatio-temporal features. We evaluate SVFormer on two RGB datasets (UCF101, NTU-RGBD60) and one neuromorphic dataset (DVS128-Gesture), demonstrating comparable performance to the mainstream models in a more efficient way. Notably, SVFormer achieves a top-1 accuracy of 84.03% with ultra-low power consumption (21 mJ/video) on UCF101, which is state-of-the-art among directly trained deep SNNs, showcasing significant advantages over prior models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

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：