检索结果-内蒙古大学图书馆

Far-field super-resolution chemical microscopy

Light(science & Applications) 2023年第7期12卷 1246-1267页

作者： Mingwei Tang Yubing Han Danchen Jia Qing Yang Ji-Xin Cheng State Key Laboratory of Modern Optical Instrumentation College of Optical Science and EngineeringZhejiang UniversityHangzhou 310027China Intelligent Perception Research Institute Zhejiang LabHangzhou 311100China Department of Biomedical Engineering Department of Electrical and Computer EngineeringPhotonics CenterBoston UniversityBostonMA 02459USA

Far-feld chemical microscopy providing molecular electronic or vibrational fingerprint information opens a new window for the study of three-dimensional biological,material,and chemical *** microscopy provides a nondestructive way of chemical identification without exterior ***,the diffraction limit of optics hindered it from discovering more details under the resolution *** development of super-resolution techniques gives enlightenment to open this door behind far-field chemical ***,we review recent advances that have pushed the boundary of far-field chemical microscopy in terms of spatial *** further highlight applications in biomedical research,material characterization,environmental study,cultural heritage conservation,and integrated chip inspection.

关键词： chemical details optics

来源：评论

学校读者我要写书评

暂无评论

CAT: a coarse-to-fine attention tree for semantic change detection

引用

Visual Intelligence 2023年第1期1卷 1-12页

作者： Wei, Xiu-Shen Xu, Yu-Yan Zhang, Chen-Lin Xia, Gui-Song Peng, Yu-Xin School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Integrated Services Networks Xidian University Xi’an China Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing China 4Paradigm Inc Beijing China School of Computer Science and Institute of Artificial Intelligence Wuhan University Wuhan China Wangxuan Institute of Computer Technology Peking University Beijing China

Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as “water-vegetation” and “water-tree”, which can be regarded as fine-grained differences. In addition, even a single LCM category is usually difficult to define. For instance, some “vegetation” categories with litter vegetation coverage are easily confused with the general “ground” category. SCD/LCM becomes challenging under both challenges of its fine-grained nature and label ambiguity. In this paper, we tackle the SCD and LCM tasks simultaneously by proposing a coarse-to-fine attention tree (CAT) model. Specifically, it consists of an encoder, a decoder and a coarse-to-fine attention tree module. The encoder-decoder structure extracts the high-level features from input multi-temporal images first and then reconstructs them to return SCD and LCM predictions. Our coarse-to-fine attention tree, on the one hand, utilizes the tree structure to better model a hierarchy of categories by predicting the coarse-grained labels first and then predicting the fine-grained labels later. On the other hand, it applies the attention mechanism to capture discriminative pixel regions. Furthermore, to address label ambiguity in SCD/LCM, we also equip a label distribution learning loss upon our model. Experiments on the large-scale SECOND dataset justify that the proposed CAT model outperforms state-of-the-art models. Moreover, various ablation studies have demonstrated the effectiveness of tailored designs in the CAT model for solving semantic change detection problems. © The Author(s) 2023.

关键词： Attention tree Coarse-to-fine Fine-grained recognition label ambiguity Semantic change detection

来源：评论

学校读者我要写书评

暂无评论

BAG OF TRICKS WITH QUANTIZED CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION

arXiv

引用

arXiv 2023年

作者： Hu, Jie Zeng, Mengze Wu, Enhua State Key Laboratory of Computer Science ISCAS Saudi Arabia University of Chinese Academy of Sciences China ByteDance Inc. China University of Macau China

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have been proposed to reduce the memory footprint and improve inference speed. While numerous quantization methods have been proposed, they lack systematic analysis for their effectiveness. To bridge this gap, we collect and improve existing quantization methods and propose a gold guideline for post-training quantization. We evaluate the effectiveness of our proposed method with two popular models, ResNet50 and MobileNetV2, on the ImageNet dataset. By following our guidelines, no accuracy degradation occurs even after directly quantizing the model to 8-bits without additional training. A quantization-aware training based on the guidelines can further improve the accuracy in lower-bits quantization. Moreover, we have integrated a multi-stage fine-tuning strategy that works harmoniously with existing pruning techniques to reduce cost even further. Remarkably, our results reveal that a quantized MobileNetV2 with 30% sparsity actually surpasses the performance of the equivalent full-precision model, underscoring the effectiveness and resilience of our proposed scheme. © 2023, CC BY-NC-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation 41

Safe Reinforcement Learning using Finite-Horizon Gradient-ba...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Dai, Juntao Yang, Yaodong Zheng, Qian Pan, Gang College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China Center for AI Safety and Governance Peking University Beijing China

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation (ABE) method relies on the infinite-horizon discounted advantage function. This dependence leads to catastrophic errors in finite-horizon scenarios with non-discounted constraints, resulting in safety-violation updates. In response, we propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL, termed Gradient-based Estimation (GBE), which relies on the analytic gradient derived along trajectories. Our theoretical and empirical analyses demonstrate that GBE can effectively estimate constraint changes over a finite horizon. Constructing a surrogate optimization problem with GBE, we developed a novel Safe RL algorithm called Constrained Gradient-based Policy Optimization (CGPO). CGPO identifies feasible optimal policies by iteratively resolving sub-problems within trust regions. Our empirical results reveal that CGPO, unlike baseline algorithms, successfully estimates the constraint functions of subsequent policies, thereby ensuring the efficiency and feasibility of each update. Copyright 2024 by the author(s)

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting 38

DRIP: Unleashing Diffusion Priors for Joint Foreground and A...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xiaodi Yang, Zongxin Quan, Ruijie Yang, Yi The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China CCAI College of Computer Science and Technology Zhejiang University Hangzhou China DBMI HMS Harvard University Boston United States

Recovering the foreground color and opacity/alpha matte from a single image (i.e., image matting) is a challenging and ill-posed problem where data priors play a critical role in achieving precise results. Due to the limited matting datasets, traditional methods usually struggle to produce high-quality *** address this, we explore the potential of leveraging vision priors embedded in pre-trained latent diffusion models (LDM) for estimating foreground RGBA values in challenging scenarios and rare objects. We introduce Drip, a novel approach for image matting that harnesses the rich prior knowledge of LDM models. Our method incorporates a switcher and a cross-domain attention mechanism to extend the original LDM for joint prediction of the foreground color and opacity. This setup facilitates mutual information exchange and ensures high consistency across both modalities. To mitigate the inherent reconstruction errors of the LDM's VAE decoder, we propose a latent transparency decoder to align the RGBA prediction with the input image, thereby reducing discrepancies. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art performance in foreground and alpha predictions and shows remarkable generalizability across various 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

PhantomPatch: Easy-ignoring Attacks on Object Detectors Using Ghosting Artifacts 22

PhantomPatch: Easy-ignoring Attacks on Object Detectors Usin...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Guo, Xiaolong Yao, Qingsong Li, Jingwei Dong, Xuewen Ma, Jianfeng Xidian University School of Cyber Engineering Xi'an China Xidian University State Key Lab of Isn School of Telecommunications Engineering Xi'an China Xidian University School of Computer Science and Technology Xi'an China

ISBN: (纸本)9798331509712

Current patches used to attack object detectors are easily noticeable as abnormal. To mitigate this shortcoming, we devise an innovative technique named PhantomPatch, which leverages lens flare phenomena to attack object detectors, particularly in autonomous driving systems. Leveraging transfer-based adversarial examples, this method fools object detectors by projecting deceptive lens flares or ghost images, which are meaningless to people, while the light source looks like nearby light for people. Thus, it is easy to *** this way, we enable a cost-effective approach to manipulate the perception of the vehicle remotely. This strategy harmonizes adversarial patches with projecting image integrity correcting. Firstly, we propose to train a black-box transfer-based adversarial patch to fool the object-detecting system behind the camera. Then, the patch is printed and attached in front of a flashlight, which casts the patch onto the camera, resulting in a ghost image. We maintain the integrity of the image captured by the camera while casting the patch with image loss correction and optical distortion *** experimental results validate the effectiveness of PhantomPatch in evading existing object detectors such as YOLO V3/V5 and Faster R-CNN. Notably, during nocturnal scenarios, the technique achieves a success rate of 98.2%. Furthermore, our approach addresses limitations of existing methods, like conspicuousness and positional constraints, offering a low-cost and effective technique for adversarial attacks, especially for autonomous vehicles. Code and demo are available at https://***/rufus0803/PhantomPatch. © 2024 IEEE.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Explainable data transformation recommendation for automatic visualization

引用

Frontiers of Information Technology & Electronic Engineering 2023年第7期24卷 1007-1027页

作者： Ziliang WU Wei CHEN Yuxin MA Tong XU Fan YAN Lei LV Zhonghao QIAN Jiazhi XIA State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China School of Computer Science and Engineering Central South UniversityChangsha 410083China

Automatic visualization generates meaningful visualizations to support data analysis and pattern finding for novice or casual users who are not familiar with visualization *** automatic visualization approaches adopt mainly aggregation and filtering to extract patterns from the original ***,these limited data transformations fail to capture complex patterns such as clusters and *** recent advances in feature engineering provide the potential for more kinds of automatic data transformations,the auto-generated transformations lack explainability concerning how patterns are connected with the original *** tackle these challenges,we propose a novel explainable recommendation approach for extended kinds of data transformations in automatic *** summarize the space of feasible data transformations and measures on explainability of transformation operations with a literature review and a pilot study,respectively.A recommendation algorithm is designed to compute optimal transformations,which can reveal specified types of patterns and maintain *** demonstrate the effectiveness of our approach through two cases and a user study.

关键词： Data transformation Data transformation recommendation Automatic visualization Explainability

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

引用

ACM Transactions on Intelligent Systems and Technology 2024年第6期15卷 1-28页

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Suzhou China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education and Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University AuburnAL United States Department of Electrical and Computer Engineering North Carolina State University RaleighNC United States Bedi Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this article, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent tradeoff between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Selective Parameter Sharing Mechanism Embedded with Multi-Level Reasoning Abstractions 26

A Dynamic Selective Parameter Sharing Mechanism Embedded wit...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Liu, Yan He, Ying Ming, Zhong Yu, F. Richard Shenzhen Key Lab of Digital & Intelligent Technologies & Systems College of Computer Science and Software Engineering Shenzhen University China State Key Laboratory of Integrated Services Networks Xidian University China Shenzhen China

ISBN: (纸本)9781643684369

Cooperative multi-agent reinforcement learning (Co-MARL) commonly employs different parameter sharing mechanisms, such as full and partial sharing. However, imprudent application of these mechanisms can potentially constrain policy diversity and limit cooperation flexibility. Recent methods that group agents into distinct sharing categories often exhibit poor performance due to challenges in precisely differentiating agents and neglecting the issue of promoting cooperation among these categories. To address these issues, we introduce a dynamic selective parameter sharing mechanism embedded with multi-level reasoning abstractions (DSPS-MA). Our approach uses self-comparison sequences to infer agents' abstract concepts, defining the differences between agents and allowing them to dynamically select partners to share parameters based on these abstract concepts. We also design an intrinsic reward to offer comprehensive collaboration guidance for agents, and introduce a policy cosine similarity regularization term to ensure sufficient policy diversity. Empirical evaluations demonstrate that our approach yields higher returns and faster convergence than state-of-the-art methods. © 2023 The Authors.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Vision GNN: An Image is Worth Graph of Nodes

arXiv

引用

arXiv 2022年

作者： Han, Kai Wang, Yunhe Guo, Jianyuan Tang, Yehui Wu, Enhua State Key Lab of Computer Science ISCAS & UCAS China Huawei Noah’s Ark Lab China Peking University China University of Macau China

Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex objects. In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. We first split the image to a number of patches which are viewed as nodes, and construct a graph by connecting the nearest neighbors. Based on the graph representation of images, we build our ViG model to transform and exchange information among all the nodes. ViG consists of two basic modules: Grapher module with graph convolution for aggregating and updating graph information, and FFN module with two linear layers for node feature transformation. Both isotropic and pyramid architectures of ViG are built with different model sizes. Extensive experiments on image recognition and object detection tasks demonstrate the superiority of our ViG architecture. We hope this pioneering study of GNN on general visual tasks will provide useful inspiration and experience for future research. The PyTorch code is available at https://***/huawei-noah/ Efficient-AI-Backbones and the MindSpore code is available at https://***/mindspore/models. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

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：