检索结果-内蒙古大学图书馆

Event-enhanced synthetic aperture imaging

Science China(information Sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Omni-dimensional dynamic convolution feature coordinate attention network for pneumonia classification

引用

visual Computing for Industry,Biomedicine,and Art 2024年第1期7卷 196-208页

作者： Yufei Li Yufei Xin Xinni Li Yinrui Zhang Cheng Liu Zhengwen Cao Shaoyi Du Lin Wang School of Information Science and Technology Northwest UniversityXi’an 710127Shaanxi ProvinceChina Department of Ultrasound the Second Affiliated Hospital of Xi’an Jiaotong UniversityXi’anShaanxi Province 710004China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applicationsand Institute of Artificial Intelligence and RoboticsXi’an Jiaotong UniversityXi’anShaanxi Province 710049China

Pneumonia is a serious disease that can be fatal,particularly among children and the *** accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray *** study proposes X-ODFCANet,which addresses the issues of low accuracy and excessive parameters in existing deep-learningbased pneumonia-classification *** network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution(ODConv)module,leveraging the residual module for feature extraction from X-ray *** feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial ***,the ODConv module extracts and fuses feature information in four dimensions:the spatial dimension of the convolution kernel,input and output channel quantities,and convolution kernel *** experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification,which is 3.77%higher than that of *** model parameters are 4.45M,which was reduced by approximately 2.5 *** code is available at https://***/limuni/X ODFCA NET.

关键词： Pneumonia Coordinate attention Dynamic convolution ResNet18 X-ODFCANet

来源：评论

学校读者我要写书评

暂无评论

Referencing Where to Focus: Improving visual Grounding with Referential Query 38

Referencing Where to Focus: Improving Visual Grounding with ...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wang, Yabing Tian, Zhuotao Guo, Qingpei Qin, Zheng Zhou, Sanping Yang, Ming Wang, Le National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Harbin Institute of Technology Shenzhen China AntGroup China

visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted considerable attention, as they directly predict the coordinates of the target object without relying on additional efforts, such as pre-generated proposal candidates or pre-defined anchor boxes. However, existing research primarily focuses on designing stronger multi-modal decoder, which typically generates learnable queries by random initialization or by using linguistic embeddings. This vanilla query generation approach inevitably increases the learning difficulty for the model, as it does not involve any target-related information at the beginning of decoding. Furthermore, they only use the deepest image feature during the query learning process, overlooking the importance of features from other levels. To address these issues, we propose a novel approach, called RefFormer. It consists of the query adaption module that can be seamlessly integrated into CLIP and generate the referential query to provide the prior context for decoder, along with a task-specific decoder. By incorporating the referential query into the decoder, we can effectively mitigate the learning difficulty of the decoder, and accurately concentrate on the target object. Additionally, our proposed query adaption module can also act as an adapter, preserving the rich knowledge within CLIP without the need to tune the parameters of the backbone network. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method, outperforming state-of-the-art approaches on five visual grounding benchmarks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning 38

TPR: Topology-Preserving Reservoirs for Generalized Zero-Sho...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Chen, Hui Liu, Yanbin Ma, Yongqiang Zheng, Nanning Yu, Xin National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Auckland University of Technology New Zealand The University of Queensland Australia

Pre-trained vision-language models (VLMs) such as CLIP have shown excellent performance for zero-shot classification. Based on CLIP, recent methods design various learnable prompts to evaluate the zero-shot generalization capability on a base-to-novel setting. This setting assumes test samples are already divided into either base or novel classes, limiting its application to realistic scenarios. In this paper, we focus on a more challenging and practical setting: generalized zero-shot learning (GZSL), i.e., testing with no information about the base/novel division. To address this challenging zero-shot problem, we introduce two unique designs that enable us to classify an image without the need of knowing whether it comes from seen or unseen classes. Firstly, most existing methods only adopt a single latent space to align visual and linguistic features, which has a limited ability to represent complex visual-linguistic patterns, especially for fine-grained tasks. Instead, we propose a dual-space feature alignment module that effectively augments the latent space with a novel attribute space induced by a well-devised attribute reservoir. In particular, the attribute reservoir consists of a static vocabulary and learnable tokens complementing each other for flexible control over feature granularity. Secondly, finetuning CLIP models (e.g., prompt learning) on seen base classes usually sacrifices the model's original generalization capability on unseen novel classes. To mitigate this issue, we present a new topology-preserving objective that can enforce feature topology structures of the combined base and novel classes to resemble the topology of CLIP. In this manner, our model will inherit the generalization ability of CLIP through maintaining the pairwise class angles in the attribute space. Extensive experiments on twelve object recognition datasets demonstrate that our model, termed Topology-Preserving Reservoir (TPR), outperforms strong baselines including both pro

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point cloud segmentation network based on multi-scale feature fusion

Point cloud segmentation network based on multi-scale featur...

引用

2024 China Automation Congress, CAC 2024

作者： Deng, Hao Cheng, Peng Cheng, Shengmei Liu, Cheng Du, Shaoyi Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Service School of Information Science and Technology Northwest University Xi’an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9798350368604

Aiming at improving the local feature extraction for point cloud learning, we introduce a point cloud segmentation network that enhances the PointNet++ framework with a local feature transformation module and a multi-scale feature fusion module. The local feature transformation module employs operations akin to convolution to restructure the point cloud's local feature dimensions, thus boosting the network's ability to extract detailed local features. Additionally, the multi-scale feature fusion module integrates semantic features of point clouds across various scales using a layered network design, aiming to heighten segmentation precision. Experimental results indicate that the proposed network can achieve a robust point cloud segmentation accuracy, reaching an accuracy rate of 85.8%. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration 38

Measuring Mutual Policy Divergence for Multi-Agent Sequentia...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Dou, Haowen Dang, Lujuan Luan, Zhirong Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence China National Engineering Research Center for Visual Information and Applications China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China School of Electrical Engineering Xi'an University of Technology China

Despite the success of Multi-Agent Reinforcement Learning (MARL) algorithms in cooperative tasks, previous works, unfortunately, face challenges in heterogeneous scenarios since they simply disable parameter sharing for agent specialization. Sequential updating scheme was thus proposed, naturally diversifying agents by encouraging agents to learn from preceding ones. However, the exploration strategy in sequential scheme has not been investigated. Benefiting from updating one-by-one, agents have the access to the information from preceding agents. Thus, in this work, we propose to exploit the preceding information to enhance exploration and heterogeneity sequentially. We present Multi-Agent Divergence Policy Optimization (MADPO), equipped with mutual policy divergence maximization framework. We quantify the discrepancies between episodes to enhance exploration and between agents to heterogenize agents, termed intra-agent divergence and inter-agent divergence. To address the issue that traditional divergence measurements lack stability and directionality, we propose to employ the conditional Cauchy-Schwarz divergence to provide entropy-guided exploration incentives. Extensive experiments show that the proposed method outperforms state-of-the-art sequential updating approaches in two challenging multi-agent tasks with various heterogeneous scenarios. Source code is available at https://***/hwdou6677/MADPO. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hidden States in LLMs Improve EEG Representation Learning and visual Decoding 27

Hidden States in LLMs Improve EEG Representation Learning an...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Liu, Aoyang Jing, Haodong Liu, Yulong Ma, Yongqiang Zheng, Nanning National Key Laboratory of Human-Machine Hybrid Augmented Intelligence China National Engineering Research Center of Visual Information and Applications China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9781643685489

Analyzing brain signals and reconstructing visual stimuli from the brain can facilitate further exploration on cognitive functions of the human brain, which have attracted strong interest in neuroscience and artificial intelligence. However, due to defects such as complex noises and the lack of alignment accuracy, efficient methods for extracting information from Electroencephalogram (EEG) signals are still very limited, making it difficult to perform EEG visual decoding tasks. Our study shows a way to handle the issues by proposing a new method for EEG representation learning and visual decoding, thus completing end-to-end image reconstruction tasks from EEG signals. We utilize the ability of semantic extraction and prediction of large language models (LLMs) to enhance the performance of EEG feature extraction. For semantic representation learning, we align EEG signals with target semantic embeddings, which are obtained from hidden states of Large Language Model Meta AI 2 (LLaMa-2) by inputting descriptions of images into the model. We also extract visual features from EEG signals to improve the quantity of the reconstructed images at low levels. Then we fuse semantic features and visual features by applying a pre-trained diffusion model and finally generate the corresponding images. We are the first to incorporate the LLM into EEG visual decoding tasks. Our method achieves the state-of-the-art result of EEG classification accuracy and the quality of reconstructed images on ImageNet-EEG datasets. In one word, our work is an important step forward in the field of exploiting the relationship between language models and human visual cognition. Our codes are available at https://***/lay-atsa/llm4eeg. © 2024 The Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lightweight Remote Sensing Semantic Segmentation via Weak Consistency Regularization

Enhancing Lightweight Remote Sensing Semantic Segmentation v...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zirong Chen Shunxin Xiao Wang Man Da-Han Wang Yifan He Shunzhi Zhu School of Computer and Information Engineering Xiamen University of Technology Xiamen China Xiamen Key Laboratory of Visual Perception Technology and Applications Reconova Technologies Co. Ltd Xiamen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Remote sensing image semantic segmentation has widespread applications in urban planning and land monitoring. In recent years, U-Net and its variant networks have almost dominated the research in the field of semantic segmentation. However, many models pay less attention to computational efficiency, rendering them ineffective in scenarios with computational resource and timeliness constraints, such as autonomous driving and disaster monitoring. To address this issue, we propose the USA-Net (UNet-like with Shifted Axial), a lightweight hybrid model based on convolution and MLP (Multi-Layer Perceptron). Specifically, we design the ST Block (Shift Tokenized Block), which introduces local features into global operations in MLP through spatial shift, and then use ELCM (Efficient Large-kernel Convolution Module) to enlarge the model’s receptive field and learn the shape features of objects. Additionally, we propose a new semi-supervised learning framework to further improve the model’s generalization performance. On the ISPRS Vaihingen and ISPRS Potsdam datasets, USA-Net significantly outperforms most state-of-the-art methods in terms of segmentation accuracy and efficiency.

关键词： Accuracy Convolution Shape Semantic segmentation Computational modeling Urban planning Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

MOA-Net: Multilevel Object Aware Network for Remote Sensing Image Semantic Segmentation

MOA-Net: Multilevel Object Aware Network for Remote Sensing ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： YuHan Chen Yun Wu JiaHua Wu Da-Han Wang YiFan He School of Computer and Information Engineering Xiamen University of Technology Xiamen China Xiamen Key Laboratory of Visual Perception Technology and Applications Reconova Technologies Co.Ltd Xiamen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Remote sensing image semantic segmentation is an essential aspect of the intelligent analysis of remote sensing, extensively applied in urban planning, economic assessment, and disaster monitoring. However, the expansive field of view and intricate backgrounds in remote sensing images cause numerous objects of varying sizes and categories to coexist. This results in incomplete object segmentation and poses challenges in restoring the spatial distribution of objects. In this paper, we present a Multilevel Object Aware Network (MOA-Net), which addresses the challenges of remote sensing image semantic segmentation. To be specific, this method is designed from three perspectives. Firstly, we establish a Progressive Multiscale Global-Local Decoder (PMGLD), integrating global-local context information of objects at varying scales through a progressive convolution strategy. Secondly, the Orientation-Aware Attention Mechanism (OAAM) provides orientation information and guides the restoration of interclass 2-D spatial relationships. Finally, obtaining fine-grained features through CNN Stem improves edge segmentation. Experimental outcomes on the Potsdam and Vaihingen datasets indicate that our method of performance and efficiency surpass those of existing methods.

关键词： Graphical models Semantic segmentation Image edge detection Urban planning Neural networks Object segmentation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Multi-View fMRI Model with Voxel Inner State for Vision Encoding

A Multi-View fMRI Model with Voxel Inner State for Vision En...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Yueying Wu, Hao Chen, Badong Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Xi'an710049 China School of Electrical Engineering Xi'An University of Technology Xi'an710048 China

ISBN: (纸本)9798350303759

visual encoding and decoding is an important tool to explore brain neural function, how to establish an efficient and accurate encoding model is an important issue in fMRI brain visual encoding tasks. However, due to the low signal-to-noise ratio and the high-dimensional characteristics of fMRI signal, it is difficult to extract response component from voxels which has high correlation with external image stimulus. Traditional fMRI encoding models ignore the voxel inner state and noise components in fMRI response, In this work, We present a novel approach of encoding by adding voxel mode into the encoding stage, which is ignored in previous study. We propose a multi-view voxel-wise encoding model with two input modes, independently extract voxel features and stimuli features. Our multi-view encoding model takes voxel inner state into encoding stage, and uses feature-irrelevant voxels to perform noise reduction for feature-relevant voxels simultaneously, thus reach a higher explain variance (R2) of encoding result and higher image identification accuracy of decoding result. Our work is helpful for further exploring the characteristics of visual cortex and understanding the mechanism of brain visual pathway. © 2023 IEEE.

关键词： Signal to noise ratio

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：