检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhuo Huang Miaoxi Zhu Xiaobo Xia Li Shen Jun Yu Chen Gong Bo Han Bo Du Tongliang Liu Sydney AI Centre The University of Sydney National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University JD Explore Academy Department of Automation University of Science and Technology of China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Department of Computer Science Hong Kong Baptist University

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is available, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Student Inference Network for Efficient Single Image Super-Resolution

Adaptive Student Inference Network for Efficient Single Imag...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Kang Miao Zhao Zhang Jiahuan Ren Mingbo Zhao Haijun Zhang Richang Hong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China School of Information Science and Technology Donghua University Shanghai China Department of Computer Science Harbin Institute of Technology (Shenzhen) Shenzhen China

Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning

arXiv

引用

arXiv 2023年

作者： Huo, Dongjian Zhang, Zehong Su, Hanjing Li, Guanbin Fang, Chaowei Wu, Qingyao School of Software and Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Peng Cheng Laboratory China Tencent Wechat Department School of Computer Science and Engineering Sun Yat-sen University China Xidian University China

Watermarking serves as a widely adopted approach to safeguard media copyright. In parallel, the research focus has extended to watermark removal techniques, offering an adversarial means to enhance watermark robustness and foster advancements in the watermarking field. Existing watermark removal methods mainly rely on UNet with task-specific decoder branches——one for watermark localization and the other for background image restoration. However, watermark localization and background restoration are not isolated tasks;precise watermark localization inherently implies regions necessitating restoration, and the background restoration process contributes to more accurate watermark localization. To holistically integrate information from both branches, we introduce an implicit joint learning paradigm. This empowers the network to autonomously navigate the flow of information between implicit branches through a gate mechanism. Furthermore, we employ cross-channel attention to facilitate local detail restoration and holistic structural comprehension, while harnessing nested structures to integrate multiscale information. Extensive experiments are conducted on various challenging benchmarks to validate the effectiveness of our proposed method. The results demonstrate our approach’s remarkable superiority, surpassing existing state-ofthe-art methods by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, 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

AircraftVerse: a large-scale multimodal dataset of aerial vehicle designs 23

AircraftVerse: a large-scale multimodal dataset of aerial ve...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Adam D. Cobb Anirban Roy Daniel Elenius F. Michael Heim Brian Swenson Sydney Whittington James D. Walker Theodore Bapty Joseph Hite Karthik Ramani Christopher McComb Susmit Jha Computer Science Laboratory SRI International Mechanical Engineering Division Southwest Research Institute Intelligent Systems Division Southwest Research Institute Institute of Software Integrated Systems Vanderbilt University School of Mechanical Engineering Purdue University Department of Mechanical Engineering Carnegie Mellon University

We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these cyber-physical system (CPS) designs requires the use of scientific analytical and simulation models ranging from computer- aided design tools for structural and manufacturing analysis, computational fluid dynamics tools for drag and lift computation, battery models for energy estimation, and simulation models for flight control and dynamics. AircraftVerse contains 27,714 diverse air vehicle designs - the largest corpus of engineering designs with this level of complexity. Each design comprises the following artifacts: a symbolic design tree describing topology, propulsion subsystem, battery subsystem, and other design details; a STandard for the Exchange of Product (STEP) model data; a 3D CAD design using a stereolithography (STL) file format; a 3D point cloud for the shape of the design; and evaluation results from high fidelity state-of-the-art physics models that characterize performance metrics such as maximum flight distance and hover-time. We also present baseline surrogate models that use different modalities of design representation to predict design performance metrics, which we provide as part of our dataset release. Finally, we discuss the potential impact of this dataset on the use of learning in aircraft design and, more generally, in CPS. AircraftVerse is accompanied by a data card, and it is released under Creative Commons Attribution-ShareAlike (CC BY-SA) license. The dataset is hosted at https://***/record/6525446 baseline models and code at https://***/SRI-CSL/AircraftVerse and the dataset description at https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Deep is Love in LLMs’ Hearts? Exploring Semantic Size in Human-like Cognition

arXiv

引用

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Distributed Compressed Sensing Based on Local Transformer Network

SSRN

引用

SSRN 2023年

作者： Zhou, Yu Xie, Wei Yang, Yingkai Sun, Shilong Zhang, Xiao Qin, Jun Key Laboratory of Cyber-Physical Fusion Intelligent Computing State Ethnic Affairs Commission Wuhan China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Department of Computer Science South-Central Minzu University Wuhan430074 China

Among compressed sensing algorithms, Distributed Compressed Sensing (DCS) stands out for its ability to jointly reconstruct multiple signals, making it a focal point of interest for researchers and engineers , thanks to its outstanding efficiency in signal reconstruction. In contrast to conventional approaches that depend on a priori estimates, like joint sparsity of signals, deep neural networks leverage their robust feature extraction and sequence modeling abilities to automatically capture inter-signal dependencies. This confers them with the benefits of faster solving speed and superior reconstruction accuracy. Most of the current methods, however, do not fully utilize the global dependency information between signals, while also ignoring the detailed features within the signals. Therefore, this paper proposes a Local Transformer Network for DCS (LTN-DCS). It utilizes the self-attention mechanism to extract global contextual information between the reconstructed signal sequences, while also addressing local redundancy partitioning within the signal sequences for finer-grained information capture. This approach generates probabilistic estimates of the non-zero element positions in each signal, forming the foundation for selecting basis atoms from the sampling matrix. Finally, the least-squares method is used to achieve the signal reconstruction. Through extensive experiments, the results show that our proposed method outperforms state-ofthe art DCS methods. © 2023, The Authors. All rights reserved.

关键词： Signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Performance Assessment for Leader-following UAV Formation via Belief Rule Base

Performance Assessment for Leader-following UAV Formation vi...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Haoran Zhang Mingrui Hao Ruohan Yang Keyuan Yue Zhichao Feng School of Computer Science and Information Engineering Harbin Normal University Harbin P. R. China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory School of Electronics and Information Northwestern Polytechnical University Xi’an P. R. China Department of Missile Engineering Rocket Force University of Engineering Xi’an P. R. China

The article puts focus on the the problem of performance assessment for UAV formation with leader-following structure and switching communication topology in the presence of unknown exogenous perturbations. First, two time-varying indicators are devised on the basis of the regulated outputs of the followers. Then, a trainable performance assessment model is constructed by means of belief rule base expert system (BRB) with the two time-varying indicators as the inputs and the assessment utility as the final output. At last, relevant simulation experiments are conducted to validate the practicability of the established performance assessment model for leader-following UAV formation subject to switching communication topology and unknown external perturbations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STAR-RIS and UAV Combination in MEC Networks: Simultaneous Task Offloading and Communications

引用

IEEE Transactions on Communications 2025年

作者： Xiao, Han Hu, Xiaoyan Wang, Wenjie Su, Zhou Wong, Kai-Kit Yang, Kun Xi'an Jiaotong University School of Information and Communications Engineering Xi'an710049 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China University College London Department of Electronic and Electrical Engineering Torrington Place LondonWC1E 7JE United Kingdom Yonsei University Yonsei Frontier Lab Seoul Korea Republic of Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China School of Intelligent Software and Engineering Suzhou215163 China University of Essex School of Computer Science and Electronic Engineering Essex United Kingdom

This paper explores a simultaneous tasks offloading and communications (STOC) scheme in mobile edge computing (MEC) networks, supported by the combination of simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) and the unmanned aerial vehicle (UAV). Different from the traditional MEC schemes, the proposed scheme concurrently considers the computation and communication capabilities of the MEC networks, which is actually more practical in reality. Specifically, an optimization problem is devised to maximize the weighted sum of the minimum computed task data and communication data, while ensuring the quality of service (QoS) constraints for STOC through joint design of time scheduling, resource allocation, active and passive beamforming, alongside with the UAV trajectory planning. This non-convex problem with strong couplings among variables is challenging to solve directly. Then, a novel alternating optimization method is proposed, leveraging the successive convex approximation (SCA) and semi-definite relaxation (SDR) techniques. We provide sufficient numerical results to validate the effectiveness of the proposed STOC scheme, which demonstrate that the proposed scheme supported by STAR-RIS and UAV outperforms five benchmark schemes in terms of performance gain. It is important to note that the proposed scheme offers a feasible and realistic way for the implementations of STOC in practical MEC networks. © 1972-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty

arXiv

引用

arXiv 2022年

作者： Xu, Wenting Xu, Zhenghua Chen, Junyang Qi, Chang Lukasiewicz, Thomas State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science University of Oxford United Kingdom

To reduce doctors’ workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where deep convolutional neural networks (CNNs) are employed to encode the input images, and recurrent neural networks (RNNs) are used to decode the visual features into medical reports automatically. However, these state-of-the-art methods mainly suffer from three shortcomings: (i) incomprehensive optimization, (ii) low-order and unidimensional attention mechanisms, and (iii) repeated generation. In this article, we propose a hybrid reinforced medical report generation method with m-linear attention and repetition penalty mechanism (HReMRG-MR) to overcome these problems. Specifically, a hybrid reward with different weights is employed to remedy the limitations of single-metric-based rewards. We also propose a search algorithm with linear complexity to approximate the best weight combination. Furthermore, we use m-linear attention modules to explore high-order feature interactions and to achieve multi-modal reasoning, while a repetition penalty applies penalties to repeated terms during the model’s training process. Extensive experimental studies on two public datasets show that HReMRG-MR greatly outperforms the state-of-the-art baselines in terms of all metrics. We also conducted a series of ablation experiments to prove the effectiveness of all our proposed components. We also performed a reward search toy experiment to give evidence that our proposed search approach can significantly reduce the search time while approximating the best performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：