检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dai, Mingliang Huang, Zhizhong Gao, Jiaqi Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

Noisy annotations such as missing annotations and location shifts often exist in crowd counting datasets due to multi-scale head sizes, high occlusion, etc. These noisy annotations severely affect the model training, especially for density map-based methods. To alleviate the negative impact of noisy annotations, we propose a novel crowd counting model with one convolution head and one transformer head, in which these two heads can supervise each other in noisy areas, called Cross-Head Supervision. The resultant model, CHS-Net, can synergize different types of inductive biases for better counting. In addition, we develop a progressive cross-head supervision learning strategy to stabilize the training process and provide more reliable supervision. Extensive experimental results on ShanghaiTech and QNRF datasets demonstrate superior performance over state-of-the-art methods. Code is available at https://***/RaccoonDML/CHSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Online Learning Behavior Analysis and Prediction Based on Spiking Neural Networks

引用

Journal of Social computing 2024年第2期5卷 180-193页

作者： Yanjing Li Xiaowei Wang Fukun Chen Bingxu Zhao Qiang Fu the Institute of Education Science Research Heilongjiang UniversityHarbin 150080China the School of Cyberspace Security Shandong University of Political Science and LawJinan 250014China the School of Computer Science and Technology Harbin Engineering UniversityHarbin 150001China the Faculty of Electrical and Computer Engineering University of VictoriaVictoriaV8P 5C2Canada. the Guangxi Key Lab of Brain-Inspired Computing and Intelligent Chips School of Electronic and Information EngineeringGuangxi Normal UniversityGuilin 541004China

The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of *** study utilizes the historical and final learning behavior data of over 300000 learners from 17 courses offered on the edX platform by Harvard University and the Massachusetts institute of technology during the 2012-2013 academic *** have developed a spike neural network to predict learning outcomes,and analyzed the correlation between learning behavior and outcomes,aiming to identify key learning behaviors that significantly impact these *** goal is to monitor learning progress,provide targeted references for evaluating and improving learning effectiveness,and implement intervention measures *** results demonstrate that the prediction model based on online learning behavior using spiking neural network achieves an impressive accuracy of 99.80%.The learning behaviors that predominantly affect learning effectiveness are found to be students’academic performance and level of participation.

关键词： online learning learning outcomes prediction learning behavior analysis spiking neural network

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature Fusion

arXiv

引用

arXiv 2024年

作者： Cao, Yice Liu, Chenchen Wu, Zhenhua Yao, Wenxin Xiong, Liu Chen, Jie Huang, Zhixiang The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University Hefei230601 China The 38th Research Institute China Electronics Technology Group Corporation Hefei230088 China

As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of investigation within the realm of remote sensing. Although segmentation algorithms based on CNNs and Transformers achieve significant progress in performance, balancing segmentation accuracy and computational complexity remains challenging, limiting their wide application in practical tasks. To address this, this paper introduces state space model (SSM) and proposes a novel hybrid semantic segmentation network based on vision Mamba (CVMH-UNet). This method designs a cross-scanning visual state space block (CVSSBlock) that uses cross 2D scanning (CS2D) to fully capture global information from multiple directions, while by incorporating convolutional neural network branches to overcome the constraints of Vision Mamba (VMamba) in acquiring local information, this approach facilitates a comprehensive analysis of both global and local features. Furthermore, to address the issue of limited discriminative power and the difficulty in achieving detailed fusion with direct skip connections, a multi-frequency multi-scale feature fusion block (MFMSBlock) is designed. This module introduces multi-frequency information through 2D discrete cosine transform (2D DCT) to enhance information utilization and provides additional scale local detail information through point-wise convolution branches. Finally, it aggregates multi-scale information along the channel dimension, achieving refined feature fusion. Findings from experiments conducted on renowned datasets of remote sensing imagery demonstrate that proposed CVMH-UNet achieves superior segmentation performance while maintaining low computational complexity, outperforming surpassing current leading-edge segmentation algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM

arXiv

引用

arXiv 2024年

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model’s generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. 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

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Scalable Graph Compressed Convolutions

arXiv

引用

arXiv 2024年

作者： Sun, Junshu Wang, Shuhui Yang, Chenxue Huang, Qingming The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The Agricultural Information Institute China Academy of Agricultural Sciences Beijing100081 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518066 China

Designing effective graph neural networks (GNNs) with message passing has two fundamental challenges, i.e., determining optimal message-passing pathways and designing local aggregators. Previous methods of designing optimal pathways are limited with information loss on the input features. On the other hand, existing local aggregators generally fail to extract multi-scale features and approximate diverse operators under limited parameter scales. In contrast to these methods, Euclidean convolution has been proven as an expressive aggregator, making it a perfect candidate for GNN construction. However, the challenges of generalizing Euclidean convolution to graphs arise from the irregular structure of graphs. To bridge the gap between Euclidean space and graph topology, we propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. The permutations constrain all nodes in a row regardless of their input order and therefore enable the flexible generalization of Euclidean convolution to graphs. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning. CoCN follows local feature-learning and global parameter-sharing mechanisms of convolution neural networks. The whole model can be trained end-to-end, with compressed convolution applied to learn individual node features and their corresponding structure features. CoCN can further borrow successful practices from Euclidean convolution, including residual connection and inception mechanism. We validate CoCN on both node-level and graph-level benchmarks. CoCN achieves superior performance over competitive GNN baselines. Codes are available at https://***/sunjss/CoCN. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Controlling Large Language Models Through Concept Activation Vectors 39

Controlling Large Language Models Through Concept Activation...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Hanyu Wang, Xiting Li, Chengao Ao, Xiang He, Qing Key Lab of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China Key Lab of AI Safety of Chinese Academy of Sciences (CAS) Beijing 100190 China University of Chinese Academy of Sciences CAS Beijing 100049 China Gaoling School of Artificial Intelligence Renmin University of China Beijing China

ISBN: (纸本)157735897X

As large language models (LLMs) are widely deployed across various domains, the ability to control their generated outputs has become more critical. This control involves aligning LLMs outputs with human values and ethical principles or customizing LLMs on specific topics or styles for individual users. Existing controlled generation methods either require significant computational resources and extensive trial- and-error or provide coarse-grained control. In this paper, we propose Generation with Concept Activation Vector (GCAV), a lightweight model control framework that ensures accurate control without requiring resource-extensive fine-tuning. Specifically, GCAV first trains a concept activation vector for specified concepts to be controlled, such as toxicity. During inference, GCAV steers the concept vector in LLMs, for example, by removing the toxicity concept vector from the activation layers. Control experiments from different perspectives, including toxicity reduction, sentiment control, linguistic style, and topic control, demonstrate that our framework achieves state-of-the-art performance with granular control, allowing for fine-grained adjustments of both the steering layers and the steering magnitudes for individual samples. © 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

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

引用

IEEE Transactions on intelligent Transportation Systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Selection of Cancer Biomarkers from Microarray Gene Expression Data Utilizing the Bi-Objective Optimization Method

Selection of Cancer Biomarkers from Microarray Gene Expressi...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Jiang, Hanjing Lin, Jianqing Zhu, Huachao Huang, Yabing Huazhong University of Science and Technology Key Lab. of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Wuhan430074 China Wuhan University School of Computer Science Wuhan430064 China Renmin Hospital of Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350337488

Cancer-associated biomarker genes play an indispensable role in the intricate tapestry of cancer development and manifestation. The expression of biomarkers in different types of tumor cells has beneficial implications for shedding light on the development of various cancers, guiding clinical diagnosis, and treatment. Microarray technology enables the expression levels of thousands of genes in samples to be sequenced simultaneously. However, sparse and high-dimensional microarray data present a formidable challenge in identifying biomarker genes. This study presents EREF-NSGA2, a novel method for cancer biomarker selection from microarray data, employing a hybrid gene selection approach. Firstly, the combination of the wrapper and embedded gene selection methods is proposed to filter the microarray data, which efficiently decreases the search space of the algorithm. After that, the improved NSGA-II algorithm is used to search the genes subset obtained from the previous step to reach the optimal subset of cancer biomarker genes. The proposed EREF-NSGA2 is compared with other reported methods on six cancer benchmark gene expression datasets. A detailed biological analysis is performed to analyze the relationship between the selected genes and the cancer data sets they belong to. To summarize, EREF-NSGA2 proves its effectiveness in selecting a feature subset comprising the fewest genes while maintaining the highest classification accuracy. © 2023 IEEE.

关键词： Bi-objective optimization Cancer biomarker Gene selection NSGA-II

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：