检索结果-内蒙古大学图书馆

Decomposed Neural Architecture Search for image denoising

Applied Soft computing 2022年 124卷

作者： Li, Di Bai, Yunpeng Bai, Zongwen Li, Ying Shang, Changjing Shen, Qiang School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an710129 China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University AberystwythSY233DB United Kingdom Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan'an University Yan'an716000 China

In practical applications of deep learning, as the demand for the modeling capability increases, the network size may need to be massively enlarged in response. This may form a significant challenge in practice, especially when facing the dilemma of limited computational resources, making model compression indispensable. It can be time-consuming and interminable to obtain an appropriate network architecture through manual compression. In this paper, we propose an automated method for searching decomposed network architectures, named DNAS (standing for Decomposed Neural Architecture Search). It integrates both tasks of neural architecture search and tensor decomposition based model compression within a unified framework. The method is able to efficiently find a compact network with high performance for image denoising, with respect to memory and runtime. Particularly, using one single V100 GPU, it only takes about 1.5 h to obtain a denoising network on the BSD500 dataset. Experimental results demonstrate that compared with models developed using existing methods, DNAS consumes significantly less inference time and employs much fewer trainable parameters, outperforming existing approaches on both synthetic and real-world denoising datasets. © 2022 Elsevier B.V.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A data Augmentation Method for Disease Diagnosis Based on Single Cell Omics data 2nd

A Data Augmentation Method for Disease Diagnosis Based on Si...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Zhuang, Han Zhang, Qinhu Ningbo Institute of Digital Twin Eastern Institute of Technology No. 568 Tongxin Road Zhuangshi Street Zhejiang Ningbo315201 China Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology Shanghai East Hospital School of Medicine Tongji University Shanghai200123 China

ISBN: (纸本)9789819619061

Single cell omics data has enabled bioinformatics methods to identify cell type, infer gene regulatory network and beyond. Besides these great advances, there is active research about how to predict patients’ diagnosis based on cell predicted disease status. In this study, we propose a computational method consisting of a resampling method and an AI model to perform disease diagnosis with single cell omics data. According to our analysis, our proposed method outperforms baseline methods on three public datasets and is effective for disease diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： disease diagnosis resampling single cell omics

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Graph Computation Model with Communication Equilibrium 15th

A Two-Stage Graph Computation Model with Communication Equil...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Dong, Yanmei Chen, Rongwang Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China College of Mathematics and Computer Science Wuyi University Wuyishan Fujian354300 China Digital Fujian Tourism Big Data Institute Wuyishan Fujian354300 China

ISBN: (纸本)9789811625398

Distributed graph computing aims at performing in-depth analysis on large networks in a parallel manner. Iterative communication computation is an important model to perform graph analysis. Moreover, high-efficiency iterative communication computation is necessary for assuring the quality of graph partitioning. Many strategies to improve graph computing are usually based on the hypothesis of single communication iteration which focuses on the optimization of load balance in a single graph partitioning and the improvement of parallel granularity or communication manners. However, a graph in the real-world usually requires complex communication iterations to achieve good analysis results, which often have the problems of data and communication tilting and low analysis efficiency. In this paper, we propose a two-stage graph computing model with communication equilibrium (TSMCE). The model employs a communication-equilibrated graph partitioning strategy (CEGP) for load balancing and a two-stage graph computing mode (TS) to reduce the crossing-partition communication. With the change of graph density, various factors such as load balancing, communication balancing, cross-partition transmission traffic, communication delay, and convergence speed can always maintain an efficient balance. The experiments conducted on the real-world datasets show that the communication-equilibrated graph partitioning strategy can divide a graph with high quality compared with Hash and Metis. Besides, the overall performance of our two-stage graph computing model with communication equilibrium is higher than that of the BSP model. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arxiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Agentic Knowledgeable Self-awareness

arXiv

引用

arxiv 2025年

作者： Qiao, Shuofei Qiu, Zhisong Ren, Baochang Wang, xiaobin Ru, xiangyuan Zhang, Ningyu Chen, xiang Jiang, Yong xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Alibaba Group China Nanjing University of Aeronautics and Astronautics China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a "flood irrigation" methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of situational self-awareness during decision-making—the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose agentic knowledgeable self-awareness to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose KnowSelf, a data-centric approach that applies agents with knowledgeable self-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent’s self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge1 Copyright © 2025, The Authors. All rights reserved.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

arXiv

引用

arxiv 2024年

作者： Wu, Xu Hou, xianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection

arXiv

引用

arxiv 2023年

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the Anomaly Overfitting and Homophily Trap problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate Anomaly Overfitting. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Physical Information Neural Networks for Solving High-index Differential-algebraic Equation Systems Based on Radau Methods

arXiv

引用

arxiv 2023年

作者： Chen, Jiasheng Tang, Juan Yan, Ming Lai, Shuai Liang, Kun Lu, Jianguang Yang, Wenqiang Institute of Computing Science and Technology Guangzhou University Guangzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Singapore Singapore State Key Laboratory of Public Big Data Guizhou University Guiyang China Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

As is well known, differential algebraic equations (DAEs), which are able to describe dynamic changes and underlying constraints, have been widely applied in engineering fields such as fluid dynamics, multi-body dynamics, mechanical systems and control theory. In practical physical modeling within these domains, the systems often generate high-index DAEs. Classical implicit numerical methods typically result in varying order reduction of numerical accuracy when solving high-index systems. Recently, the physics-informed neural network (PINN) has gained attention for solving DAE systems. However, it faces challenges like the inability to directly solve high-index systems, lower predictive accuracy, and weaker generalization capabilities. In this paper, we propose a PINN computational framework, combined Radau IIA numerical method with a neural network structure via the attention mechanisms, to directly solve high-index DAEs. Furthermore, we employ a domain decomposition strategy to enhance solution accuracy. We conduct numerical experiments with two classical high-index systems as illustrative examples, investigating how different orders of the Radau IIA method affect the accuracy of neural network solutions. The experimental results demonstrate that the PINN based on a 5th-order Radau IIA method achieves the highest level of system accuracy. Specifically, the absolute errors for all differential variables remains as low as 10−6, and the absolute errors for algebraic variables is maintained at 10−5, surpassing the results found in existing literature. Therefore, our method exhibits excellent computational accuracy and strong generalization capabilities, providing a feasible approach for the high-precision solution of larger-scale DAEs with higher indices or challenging high-dimensional partial differential algebraic equation systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

arXiv

引用

arxiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Token Learning for Vision-Language Tracking

arXiv

引用

arxiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

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：