检索结果-内蒙古大学图书馆

Image debanding using cross-scale invertible networks with banded deformable convolutions

NEURAL NETWORKS 2025年 187卷 107270页

作者： Quan, Yuhui He, Xuyi Xu, Ruotao Xu, Yong Ji, Hui South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China South China Univ Technol Inst Super Robot Guangzhou Peoples R China Key Lab Large Model Embodied Intelligent Humanoid Guangzhou Peoples R China Peng Cheng Lab Shenzhen Peoples R China Guangdong Prov Key Lab Multimodal Big Data Intelli Guangzhou Peoples R China Natl Univ Singapore Dept Math Singapore Singapore

Banding artifacts in images stem from limitations in color bit depth, image compression, or over-editing, significantly degrades image quality, especially in regions with smooth gradients. Image debanding is about eliminating these artifacts while preserving the authenticity of image details. This paper introduces a novel approach to image debanding using a cross-scale invertible neural network (INN). The proposed INN is information-lossless and enhanced by amore effective cross-scale scheme. Additionally, we present a technique called banded deformable convolution, which fully leverages the anisotropic properties of banding artifacts. This technique is more compact, efficient, and exhibits better generalization compared to existing deformable convolution methods. Our proposed INN exhibits superior performance in both quantitative metrics and visual quality, as evidenced by the results of the experiments.

关键词： Image debanding Invertible networks Banded deformable convolution

来源：评论

学校读者我要写书评

暂无评论

Identifying major depressive disorder based on cerebral blood flow and brain structure: An explainable multimodal learning study

引用

JOURNAL OF PSYCHIATRIC RESEARCH 2025年 182卷 304-311页

作者： Hu, Jinlong Hou, Yaqian Peng, Bo Liao, Bin Xu, Ziyun Hou, Gangqiang Dong, Shoubin South China Univ Technol Sch Comp Sci & Engn Guangdong Key Lab Multimodal Big Data Intelligent Guangzhou Peoples R China Shenzhen Kangning Hosp Shenzhen Mental Hlth Ctr Dept Depress Disorder Shenzhen Peoples R China South China Agr Univ Coll Math & Informat Guangzhou Peoples R China Shenzhen Kangning Hosp Shenzhen Mental Hlth Ctr Dept Radiol Shenzhen Peoples R China

Magnetic resonance imaging (MRI) offers non-invasive assessments of brain structure and function for analyzing brain disorders. With the increasing accumulation of multimodal MRI data in recent years, integrating information from various modalities has become an effective strategy for improving the detection of brain disorders. This study focuses on identifying major depressive disorder (MDD) by using arterial spin labeling (ASL) perfusion MRI in conjunction with structural MRI data. We collected ASL and structural MRI data from 260 participants, including 169 MDD patients and 91 healthy controls. We developed an explainable fusion method to identify MDD, utilizing cerebral blood flow (CBF) data from ASL perfusion MRI and brain tissue volumes from structural MRI. The fusion model, which integrates multimodal data, demonstrated superior predictive performance for MDD. By combining MRI regional volumes with CBF data, we achieved more effective results than using each modality independently. Additionally, we analyzed feature importance and interactions to explain the fusion model. We identified fourteen important features, comprising eight regional volumes and six regional CBF measures, that played a crucial role in the identification of MDD. Furthermore, we found three feature interactions among the important features and seven interactions between structural and functional features, which were particularly prominent in the model. The results of this study suggest that the fusion learning approach, which integrates ASL and structural MRI data, is effective in detecting MDD. Moreover, the study demonstrates that the model explanation method can reveal key features that influence the decisions of models, as well as potential interactions among these key features or between functional and structural features in identifying MDD.

关键词： Major depressive disorder multimodal learning Structural MRI Arterial spin labeling perfusion MRI

来源：评论

学校读者我要写书评

暂无评论

Adaptive disentangled target representation for unsupervised domain adaptation in remote sensing segmentation

引用

Engineering Applications of Artificial Intelligence 2025年 156卷

作者： Lu, Runuo Dong, Shoubin Jia, Jianxin Wang, Xusheng Liu, Kai Chen, Jinsong Guo, Shanxin Zheng, Xiaorou Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou510641 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute EspooFI-02150 Finland Center for Geo-Spatial Information Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application Shenzhen518055 China

Due to the significant differences between the source and target domains, semantic segmentation models for remote sensing images trained on the source domain often struggle to generalize effectively to new target domains, leading to performance degradation. Most solutions disentangle features into domain-invariant features shared by both domains and domain-specific features unique to each domain, relying primarily on the domain-invariant features for model construction and inference. However, during this process, critical domain-specific features as essential information are often discarded as noise, leading to a reduction in segmentation accuracy. To address these issues, this study proposes an unsupervised domain adaptation, called ChameleonRS. ChameleonRS separates the domain-invariant features and the domain-specific features by disentanglement learning, and introduces a multi-level feature alignment module to enhance the representation of domain-invariant features. More importantly, it aligns predictions based on domain-invariant features with those based on fused invariant and specific features using contrastive learning, effectively capturing target-specific features. This study explores two cross-domain semantic segmentation tasks: (I) Geographic location variation. (II) Geographic location and imaging mode variation. Results show that under setting (I), ChameleonRS outperforms the state-of-the-art method by 4.79% in Intersection over Union (IoU) and 6.51% in the F1 score. Under setting (II), it achieves improvements of 4.46% and 4.82% in IoU and F1 score. Results demonstrate the superiority and adaptability of ChameleonRS under varying geographical and imaging conditions, effectively mitigating the generalization issues caused by distribution differences, and thereby promoting the development and application of remote sensing technologies in practical scenarios. © 2025 Elsevier Ltd

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards reliable and damage-less robotic fragile fruit grasping: An enveloping gripper with multimodal strategy inspired by Asian elephant trunk

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 234卷

作者： Wang, Qingyu Bai, Kaixin Zhang, Lei Sun, Zhizhong Jia, Tianze Hu, Dong Li, Qiang Zhang, Jianwei Knoll, Alois Jiang, Huanyu Zhou, Mingchuan Ying, Yibin Zhejiang Univ Coll Biosyst Engn & Food Sci Hangzhou 310058 Zhejiang Peoples R China Zhejiang Univ Zhejiang Key Lab Intelligent Sensing & Robot Agr Hangzhou 310058 Peoples R China Minist Agr & Rural Affairs Key Lab Site Proc Equipment Agr Prod Beijing 310058 Peoples R China Univ Hamburg Dept Informat TAMS Tech Aspects Multimodal Syst D-22527 Hamburg Germany Agile Robots D-81477 Munich Germany Zhejiang A&F Univ Coll Chem & Mat Engn Hangzhou 311300 Zhejiang Peoples R China Zhejiang A&F Univ Coll Opt Mech & Elect Engn Hangzhou 311300 Zhejiang Peoples R China Shenzhen Technol Univ Coll Big Data & Internet Shenzhen 518118 Guangdong Peoples R China Tech Univ Munich Dept Comp Sci D-999035 Munich Germany

Fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry, which involve continuous pick-and-place manipulation. In this case, we aim to replace manual working with robotic grasping. However, for robotic fragile fruit grasping, the main difficulty is to reduce early stage bruise while maintaining the grasping reliability. In this study, we aim to solve this problem and achieve reliable and damageless robotic fragile fruit grasping. Inspired by the structure of the Asian elephant trunk with its feeding behavior, a bionic and pneumatic soft gripper was designed, and a multimodal grasping strategy was proposed. Similar with Asian elephant trunk, the gripper has two designed trapezoid air chambers to control the two individual parts, including fingertip-like process and enveloping structure. Enveloping grasping behavior was imitated with larger area of contact, less contact force, and larger pull off force. A visuo-tactile multimodal grasping strategy was integrated into the robotic grasping system. The visual modality was developed for positioning and grasp pose estimation. The tactile modality was employed for grasping pose confirmation and closed-loop grasping force control. In the experiment on the enveloping gripper, the maximum contact force and the pull off force reached a good balance and were 0.7083 N and 7.959 N, respectively. With the proposed multimodal grasping strategy, the grasping success rate increased 4.23 % to 96.70 %. As for closed-loop control of the grasping force, the average value for steady-state error and maximum overshoot were 0.0856 N and 26.43 %, respectively. The experiment on Spatial Frequency Domain Imaging (SFDI) demonstrated the effectiveness of our enveloping gripper in reducing the early stage bruise. To some extent, the designed enveloping gripper with the proposed multimodal strategy could achieve reliable and damage-less fragile fruit grasping, which is promising in fruit postharvest industr

关键词： Robotic grasping Bionic design Visuo-tactile perception Pneumatic-driven soft gripper Postharvest industry

来源：评论

学校读者我要写书评

暂无评论

UniAdapter: All-in-One Control for Flexible Video Generation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Cong Hu, Panwen Zhao, Haoyu Guo, Yuanfan Gu, Jiaxi Dong, Xiao Han, Jianhua Xu, Hang Liang, Xiaodan Chinese University of Hong Kong Hong Kong School of Science and Engineering Shenzhen China Fudan University School of Computer Science and Technology Shanghai China Huawei Noah'ark Lab Shanghai201206 China Sun Yat-Sen University School of Artificial Intelligence Zhuhai Campus Zhuhai519082 China Shenzhen Campus of Sun Yat-sen University School of Intelligent Systems Engineering Guangdong No. 66 Gongchang Road Guangming District Shenzhen518107 China Peng Cheng Laboratory and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

Condition-based video generation aims to create video content based on given information that describes specific subjects. However, most existing works can only utilize a single condition to guide the denoising process, thereby limiting their applicability to specific scenarios. Although some works attempt to accommodate multiple conditions within one framework, they often require multiple encoders, leading to inefficiencies in integrating multi-condition features. In this work, we present a framework that, with the support of the proposed Unified Adapter (UniAdapter), enables simultaneous multi-condition control of video generation within a single model. To effectively merge these conditions, we propose a novel Probabilistic Multi-condition Concatenator (PMC) module, which employs a unified encoder to accommodate multiple conditions and concatenate condition features at the pixel level to achieve fine-grained control. Following the PMC module, we employ 2D down-sampling blocks to refine features for injection into the Video Diffusion Model (VDM). Moreover, our UniAdapter is designed to be model-agnostic and compatible with any U-Net-based VDM, offering a versatile solution for improving video generation quality. Experimental results on public benchmarks UCF-101 and MSR-VTT show that our method achieves superior results in both quantitative and qualitative evaluations. © 2025 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Enhancing Underwater Images via Asymmetric Multi-Scale Invertible Networks 24

Enhancing Underwater Images via Asymmetric Multi-Scale Inver...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Quan, Yuhui Tan, Xiaoheng Huang, Yan Xu, Yong Ji, Hui South China University of Technology Guangzhou China National University of Singapore Singapore Singapore Pazhou Lab Guangzhou China Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis Guangzhou China

ISBN: (纸本)9798400706868

Underwater images, often plagued by complex degradation, pose significant challenges for image enhancement. To address these challenges, the paper redefines underwater image enhancement as an image decomposition problem and proposes a deep invertible neural network (INN) that accurately predicts both the latent image and the degradation effects. Instead of using an explicit formation model to describe the degradation process, the INN adheres to the constraints of the image decomposition model, providing necessary regularization for model training, particularly in the absence of supervision on degradation effects. Taking into account the diverse scales of degradation factors, the INN is structured on a multi-scale basis to effectively manage the varied scales of degradation factors. Moreover, the INN incorporates several asymmetric design elements that are specifically optimized for the decomposition model and the unique physics of underwater imaging. Comprehensive experiments show that our approach provides significant performance improvement over existing methods. © 2024 ACM.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yang, Yutian Liang, Lingyu Yan, Jie Xu, Yong South China University of Technology Guangzhou510641 China Henan Key Laboratory of Chronic Disease Prevention and Therapy & Intelligent Health Management Henan China Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis 510641 China

ISBN: (纸本)9781665410205

Triangular meshes provide an efficient representation of 3D shapes. Various applications such as 3D simulation suffer from degradation in geometric quality. This paper proposes a novel Multi-stream Structure-Enhanced Network (MSE-Net) based on graph convolutional networks. The network uses multi-scale features besides vertex position to guide face normal filtering, which can better preserve the geometric feature during the denoising process. In contrast to former methods that focus on filtering vertex coordinate and face normal apart, MSE-Net innovatively fuses more structure features like face area, inner product between face normal and vertex normals, and the interior angles of face to guide the face normal and vertex position updating, utilizing the inherent structural characteristic of Mesh. Our method achieves state-of-the-art performance on several publicly available datasets, demonstrating its effectiveness. © 2024 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

MBFusion: Multi-modal balanced fusion and multi-task learning for cancer diagnosis and prognosis

引用

Computers in Biology and Medicine 2024年 181卷 109042-109042页

作者： Zhang, Ziye Yin, Wendong Wang, Shijin Zheng, Xiaorou Dong, Shoubin Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510641 China

Pathological images and molecular omics are important information for predicting diagnosis and prognosis. The two kinds of heterogeneous modal data contain complementary information, and the effective fusion of the two modals can better reveal the complex mechanisms of cancer. However, due to the different representation learning methods, the expression strength of different modals in different tasks varies greatly, so that many multimodal fusions do not achieve the best results. In this paper, MBFusion is proposed, to achieve multiple tasks such as prediction of diagnosis and prognosis through multi-modal balanced fusion. The MBFusion framework uses two kinds of specially constructed graph convolutional network to extract the features of molecular omics data, and uses ResNet to extract the features of pathological image data and retain important deep features by using attention and clustering, which effectively improves both kinds of the features representation, making their expressive ability balanced and comparable. The features of these two modal data are then fused through cross-attention Transformer, and the fused features are used to learn both tasks of cancer subtype classification and survival analysis by using multi-task learning. In this paper, MBFusion and other state of the art methods are compared on two public cancer datasets, and MBFusion shows an improvement of up to 10.1% by three kinds of evaluation metrics. In the ablation experiment, MBFusion explores the contribution of each modal data and each framework module to the performance. Furthermore, the interpretability of MBFusion is explained in detail to show the value of application. © 2024 Elsevier Ltd

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

DCSim: Computing and Networking Integration based Container Scheduling Simulator for data Centers

arXiv

引用

arXiv 2024年

作者： Hu, Jinlong Rao, Zhizhe Liu, Xingchen Deng, Lihao Dong, Shoubin Guangdong Key Lab of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou China

The increasing prevalence of cloud-native technologies, particularly containers, has led to the widespread adoption of containerized deployments in data centers. The advancement of deep neural network models has increased the demand for container-based distributed model training and inference, where frequent data transmission among nodes has emerged as a significant performance bottleneck. However, traditional container scheduling simulators often overlook the influence of network modeling on the efficiency of container scheduling, primarily concentrating on modeling computational resources. In this paper, we focus on a container scheduling simulator based on collaboration between computing and networking within data centers. We propose a new container scheduling simulator for data centers, named DCSim. The simulator consists of several modules: a data center module, a network simulation module, a container scheduling module, a discrete event-driven module, and a data collection and analysis module. Together, these modules provide heterogeneous computing power modeling and dynamic network simulation capabilities. We design a discrete event model using SimPy to represent various aspects of container processing, including container requests, scheduling, execution, pauses, communication, migration, and termination within data centers. Among these, lightweight virtualization technology based on Mininet is employed to construct a software-defined network. An experimental environment for container scheduling simulation was established, and functional and performance tests were conducted on the simulator to validate its scheduling simulation capabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Training and inference Time Efficiency Assessment Framework for machine learning algorithms: A case study for hyperspectral image classification

引用

International Journal of Applied Earth Observation and Geoinformation 2025年 141卷

作者： Xiaorou Zheng Jianxin Jia Shoubin Dong Yawei Wang Runuo Lu Yuwei Chen Yueming Wang Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou 510006 China Department of Photogrammetry and Remote Sensing Finnish Geospatial Research Institute FI-02150 Espoo Finland Guangzhou Institute of Geography Guangdong Academy of Sciences Guangzhou 311100 Guangdong China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou 310024 Zhejiang China The Advanced Laser Technology Laboratory of Anhui Province Hefei 230037 China Key Laboratory of Space Active Opto-Electronics Technology Shanghai Institute of Technical Physics Chinese Academy of Sciences Shanghai 200083 China

The increasing complexity and scale of remote sensing datasets, coupled with the challenges of accurately estimating algorithmic time efficiency, often lead to significant resource waste or even failure when using machine learning algorithms in urgent or resource-constrained scenarios. Accurate time efficiency estimation is critical for deploying effective algorithms, yet it remains challenging due to the many factors influencing computational performance. Traditional methods of evaluating time efficiency often neglect the effects of core model parameters and complex data scales in spectral and temporal dimensions. In addition, inference time, an essential factor in real-world applications, is often overlooked. To address these limitations, we propose the Time Efficiency Assessment Framework (TEAF), a novel method for evaluating the time efficiency of machine learning algorithms. Through mathematical reasoning, TEAF models the training and inference time as functions ( ψ ) of complex data scales and core model parameters. The strong linear correlation between ψ and the actual runtime allows TEAF to accurately predict the time and cost of machine learning tasks with a low computational overhead before algorithm execution. To validate this framework, we derived TEAF formulations for five classical machine learning algorithms and tested them on state-of-the-art hyperspectral image datasets and Sentinel-2 multispectral datasets. The results demonstrated that TEAF could accurately predict both training and inference time for various algorithms, with a strong linear correlation between ψ and actual runtime ( R 2 > 0 . 942 ). This study offers a practical solution to the challenges posed by the increasing volume and complexity of data in remote sensing image processing. The code is available at https://***/SCUT-CCNL/TEAF .

关键词： Time efficiency Hyperspectral image Inference time Algorithm derivation Time prediction Complexity data scale

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：