检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Jing Wang, Xiaoyang Guo, Jianxiong Tang, Zhiqing Ding, Xingjian Wang, Tian Advanced Institute of Natural Sciences Beijing Normal University Zhuhai China Guangdong Key Lab of AI and Multi-modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (纸本)9789819615278

With the increasing concern for environmental protection and resource optimization, efficient waste sorting has become a serious challenge today. In this paper, we propose a new offloading control problem that aims to solve waste sorting in wireless bin communication networks. Due to limited computational power, bins belonging to embedded devices rely on simple classification models with varying accuracy. In this scenario, consider a network of intelligent bins, each acting as an independent agent capable of deciding to offload an image to the edge server with a more accurate but resource-intensive model when the local classification is deemed inaccurate. Thus, Our goal is to find a lightweight online offloading policy that can achieve the best possible sorting accuracy while balancing transmission traffic. The method utilizes a Deep Q-network algorithm that enables each intelligent bin to make image-processing decisions autonomously. In the experiment, we validate the effectiveness of improving the performance of waste classification compared with existing flow control methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed Resource Allocation Intelligent Waste Management Waste Sorting Wireless Communication network

来源：评论

学校读者我要写书评

暂无评论

PM2F2N: Patient Multi-view Multi-modal Feature Fusion networks for Clinical Outcome Prediction

PM2F2N: Patient Multi-view Multi-modal Feature Fusion Networ...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhang, Ying Zhou, Baohang Song, Kehui Sui, Xuhui Zhao, Guoqing Jiang, Ning Yuan, Xiaojie College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Mashang Consumer Finanace Co Ltd

Clinical outcome prediction is critical to the condition prediction of patients and management of hospital capacities. There are two kinds of medical data, including time series signals recorded by various devices and clinical notes in electronic health records (EHR), which are used for two common prediction targets: mortality and length of stay. Traditional methods focused on utilizing time series data but ignored clinical notes. With the development of deep learning, natural language processing (NLP) and multi-modal learning methods are exploited to jointly model the time series and clinical notes with different modals. However, the existing methods failed to fuse the multi-modal features of patients from different views. Therefore, we propose the patient multi-view multi-modal feature fusion networks for clinical outcome prediction. Firstly, from patient inner view, we propose to utilize the co-attention module to enhance the fine-grained feature interaction between time series and clinical notes from each patient. Secondly, the patient outer view is the correlation between patients, which can be reflected by the structural knowledge in clinical notes. We exploit the structural information extracted from clinical notes to construct the patient correlation graph, and fuse patients' multi-modal features by graph neural networks (GNN). The experimental results on MIMIC-III benchmark demonstrate the superiority of our method. © 2022 Association for Computational Linguistics.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

GAF-GAN: Gated Attention Feature Fusion Image Inpainting network Based on Generative Adversarial network 29

GAF-GAN: Gated Attention Feature Fusion Image Inpainting Net...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Qiu, Ran Liang, Hu Liu, Yuchen Zhao, Shengrong Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Qilu University of Technology Shandong Academy of Sciences Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Image inpainting, which aims to reconstruct reasonably clear and realistic images from known pixel information, is one of the core problems in computer vision. However, due to the complexity and variability of the underwater environment, the inability to extract valid pixel points and insufficient correlation between feature information in existing image inpainting techniques lead to blurring in the generated images. Therefore, a novel gated attention feature fusion image inpainting network based on generative adversarial networks (GAF-GAN) is proposed. The accuracy of feature similarity matching depends heavily on the validity of the information contained in the features. On the one hand, gating values are dynamically generated by gated convolution to reduce the interference of invalid information. On the other hand, semantic information at distant locations in an image is accurately acquired by the attention mechanism. For these reasons, we designed an improved gated attention mechanism. Gated attention mechanism make the network focus on effective information such as high-frequency texture and color fidelity of restored images. In addition, the dense feature fusion module is added to expand the overall receptive field of the network to fully learn the image features. Experimental results show that the proposed method can effectively repair defective images with complex texture structures and improve the reality and integrity of image details and structures. © 2023 IEEE.

关键词： Dense feature fusion module Gated attention mechanism Image inpainting Underwater environment

来源：评论

学校读者我要写书评

暂无评论

FedFLD: Heterogeneous Federated Learning via Forget-Less Distillation

FedFLD: Heterogeneous Federated Learning via Forget-Less Dis...

引用

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

作者： Xiaoyang Yi Jian Zhang Jing Chen Yuru Bao Lingkai Xing College of Cyber Science Nankai University China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China College of Computer Science Nankai University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated learning, as a distributed machine learning paradigm, enhances privacy protection but faces the challenge of heterogeneity. data-free knowledge distillation (DFKD) methods attempt to overcome this challenge by using a generator to synthesize samples for fine-tuning a global model. However, these methods often suffer from significant shifts in output distribution, leading to catastrophic forgetting. To tackle these issues, we propose FedFLD, a novel federated forget-less distillation framework that mitigates catastrophic forgetting in DFKD while addressing the heterogeneity challenge. Specifically, FedFLD guides the generator’s training from three key aspects and constrains the output distribution with an elastic weight consolidation penalty term. By synthesizing diverse samples from different perspectives through additional generator updates, FedFLD facilitates effective knowledge distillation from local models to the global model. Additionally, the global model is further optimized via the heterogeneity fine-tuning process, mitigating the bias from heterogeneity and resulting in a more expressive and robust model.

关键词： Training Privacy Federated learning Signal processing Generators Acoustics Servers Speech processing Protection Faces

来源：评论

学校读者我要写书评

暂无评论

A Span-based Multimodal Variational Autoencoder for Semi-supervised Multimodal Named Entity Recognition

A Span-based Multimodal Variational Autoencoder for Semi-sup...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Zhou, Baohang Zhang, Ying Song, Kehui Guo, Wenya Zhao, Guoqing Wang, Hongbin Yuan, Xiaojie College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Mashang Consumer Finanace Co Ltd

Multimodal named entity recognition (MNER) on social media is a challenging task which aims to extract named entities in free text and incorporate images to classify them into user-defined types. The existing semi-supervised named entity recognition methods focus on the text modal and are utilized to reduce labeling costs in traditional NER. However, the previous methods are not efficient for semi-supervised MNER. Because the MNER task is defined to combine the text information with image one and needs to consider the mismatch between the posted text and image. To fuse the text and image features for MNER effectively under semi-supervised setting, we propose a novel span-based multimodal variational autoencoder (SMVAE) model for semi-supervised MNER. The proposed method exploits modal-specific VAEs to model text and image latent features, and utilizes product-of-experts to acquire multimodal features. In our approach, the implicit relations between labels and multimodal features are modeled by multimodal VAE. Thus, the useful information of unlabeled data can be exploited in our method under semi-supervised setting. Experimental results on two benchmark datasets demonstrate that our approach not only outperforms baselines under supervised setting, but also improves MNER performance with less labeled data than existing semi-supervised methods. © 2022 Association for Computational Linguistics.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Collaboration Enhancement for Unbiased Scene Graph Generation 17

Vision-Language Collaboration Enhancement for Unbiased Scene...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Wang, Chenshu Wu, Jiying Du, Cong An, Gaoyun Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China State Administration for Market Regulation Competition Policy and Evaluation Center Beijing China China Cybersecurity Review Certification And Market Regulation Big Data Center Beijing China

ISBN: (纸本)9798350387384

Scene Graph Generation (SGG) aims to detail the visual contents of images and present them as a compact summary graph. Although several approaches have made great progress in SGG, it's still faced with the long-tailed distribution of predicates. Existing debiasing methods that focus on tail classes achieve a lot but lead to the performance degradation of head ones to some degrees. In this paper, we consider imperfect predicate feature representation is a key factor affecting the detection results of both head and tail predicates. Therefore, we focus on generating better predicate features targeting at enhancing detection capabilities for both head and tail ones. We propose a vision-language collaboration enhancement framework to obtain enhanced predicate features by fusing multiple features and context. Within this framework, we further propose an adaptive residual feature enhancement module to ensure the completeness of multi-scale features. Extensive experiments on VG dataset confirm the effectiveness of our method in improving overall performance as well as the predicate detection performance of both head and tail classes. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 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

CLIPURE: PURIFICATION IN LATENT SPACE VIA CLIP FOR ADVERSARIALLY ROBUST ZERO-SHOT CLASSIFICATION

arXiv

引用

arXiv 2025年

作者： Zhang, Mingkun Bi, Keping Chen, Wei Guo, Jiafeng Cheng, Xueqi State Key Lab of AI Safety CAS Key Lab of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts "a photo of a .". Purification is the path we choose since it does not require adversarial training on specific attack types and thus can cope with any foreseen attacks. We then formulate purification risk as the KL divergence between the joint distributions of the purification process of denoising the adversarial samples and the attack process of adding perturbations to benign samples, through bidirectional Stochastic Differential Equations (SDEs). The final derived results inspire us to explore purification in the multi-modal latent space of CLIP. We propose two variants for our CLIPure approach: CLIPure-Diff which models the likelihood of images’ latent vectors with the DiffusionPrior module in DaLLE-2 (modeling the generation process of CLIP’s latent vectors), and CLIPure-Cos which models the likelihood with the cosine similarity between the embeddings of an image and "a photo of a.". As far as we know, CLIPure is the first purification method in multi-modal latent space and CLIPure-Cos is the first purification method that is not based on generative models, which substantially improves defense efficiency. We conducted extensive experiments on CIFAR-10, ImageNet, and 13 datasets that previous CLIP-based defense methods used for evaluating zero-shot classification robustness. Results show that CLIPure boosts the SOTA robustness by a large margin, e.g., from 71.7% to 91.1% on CIFAR10, from 59.6% to 72.6% on ImageNet, and 108% relative improvements of average robustness on the 13 datasets over previous SOTA. The code is available at https://***/TMLResearchGroup-CAS/CLIPure. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

LAORA: Location-Aware Orientation Adjustment for MIMO Magnetic Wireless Charging System 21

LAORA: Location-Aware Orientation Adjustment for MIMO Magnet...

引用

21st Annual IEEE International Conference on Sensing, Communication, and networking, SECON 2024

作者： Kong, Lingchang Wang, Xinyu Zhou, Hao Zhou, Fengyu Jiang, Shenyao Zhu, Peide Song, Qi Liu, Zhi LINKE Lab School of Computer Science and Technology University of Science and Technology of China China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China China Department of Computer Science City University of Hong Kong Hong Kong School of Mathematics and Statistics Fujian Normal University Fuzhou China Department of Computer and Network Engineering The University of Electro-Communications Tokyo182-8585 Japan

ISBN: (纸本)9798331519186

Wireless power transfer (WPT) systems using magnetic resonant coupling (MRC) have made significant progress recently, leading to various optimization methods in scenarios involving multiple-input multiple-output (MIMO) to improve charging performance. Adjusting the coil orientation of the power transmitter (TX) is a simple but effective method due to the directional nature of magnetic field distribution, but existing approaches often require unnecessary coil rotations. In this study, we introduce a Location-Aware Orientation Adjustment algorithm, known as LAORA, to address these inefficiencies. LAORA focuses on solving the problems of charging devices (RX) localization and location-based optimization. We begin by introducing the concept of Equivalent Impedance Distribution Image (EIDI) and transform the RX localization problem into a combined matching process involving EIDI. In addition, we establish a dynamic simulation framework to predict charging performance using RX-related knowledge, enabling us to obtain optimal TX orientations through reinforcement learning without needing to rotate on mechanical devices physically. We then implement the prototype and conduct extensive experiments. The results show that, compared to other existing orientation adjustment methods, LAORA achieves an average improvement of 186% while reducing the mechanical rotations by 83.3%. © 2024 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5598-5614页

作者： Xue, Jingjing Sun, Sheng Liu, Min Wang, Yuwei Meng, Xuying Wang, Jingyuan Zhang, JunBo Xu, Ke Chinese Academy of Sciences Institute of Computing Technology Beijing100045 China University of Chinese Academy of Sciences Beijing101408 China Zhongguancun Lab Beijing100190 China Beihang University School of Computer Science and Engineering Beijing100191 China Beihang University MIIT Key Laboratory of Data Intelligence and Management Beijing100191 China JD Technology JD iCity JD Intelligent Cities Research Beijing101111 China Tsinghua University Department of Computer Science and Technology Beijing100190 China Zhongguancun Laboratory Beijing100081 China

For distributed network traffic prediction with data localization and privacy protection, Federated Learning (FL) enables collaborative training without raw data exchange across Base Stations (BSs). Nevertheless, traffic across BSs exhibit inherently heterogeneous trend burst and smooth fluctuation properties, but existing FL methods model single-scale series from only one view, which cannot simultaneously capture diverse trend and fluctuation properties, especially distinct burst distributions. In this paper, we propose Personalized Federated Forecasting with Multi-property Self-fusion (P2FMS), which can represent multi-scale traffic properties from different views. With precise multi-property representations, a fusion-level prediction decision is learned for each client in a personalized manner to promptly sense traffic bursts and improve forecasting performance in non-IID settings. Specifically, P2FMS decomposes the traffic series into distinct time scales, based on which, we effectively extract closeness, period, and trend properties from different views. The closeness and period are embedded through global-view representations with spatial correlations, while non-stationary trends are individually fitted from the client-side view. Furthermore, a personalized combiner is designed to accurately quantify the proportion of general fluctuation raws (i.e., closeness and period) and specific trend property in predictions, which enables multi-property self-fusion for each client to accommodate heterogeneous traffic patterns and enhance prediction accuracy. Besides, an alternant training mechanism is introduced to optimize property representation and fusion modules with the convergence guarantee. Extensive experiments on real-world datasets show that P2FMS outperforms status quo methods in both prediction performance and convergence time. © 2002-2012 IEEE.

关键词： Weather forecasting

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

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

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：