检索结果-内蒙古大学图书馆

Few-Shot Semantic Segmentation with Democratic Attention Networks 16th

学校读者我要写书评

暂无评论

Few-Shot Semantic Segmentation with Democratic Attention Net...

16th European Conference on Computer Vision, ECCV 2020

作者： Wang, Haochen Zhang, Xudong Hu, Yutao Yang, Yandan Cao, Xianbin Zhen, Xiantong Beihang University Beijing China Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beijing China AIM Lab University of Amsterdam Amsterdam Netherlands Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates YouKu Cognitive and Intelligent Lab Alibaba Group Hangzhou China

ISBN: (纸本)9783030586003

Few-shot segmentation has recently generated great popularity, addressing the challenging yet important problem of segmenting objects from unseen categories with scarce annotated support images. The crux of few-shot segmentation is to extract object information from the support image and then propagate it to guide the segmentation of query images. In this paper, we propose the Democratic Attention Network (DAN) for few-shot semantic segmentation. We introduce the democratized graph attention mechanism, which can activate more pixels on the object to establish a robust correspondence between support and query images. Thus, the network is able to propagate more guiding information of foreground objects from support to query images, enhancing its robustness and generalizability to new objects. Furthermore, we propose multi-scale guidance by designing a refinement fusion unit to fuse features from intermediate layers for the segmentation of the query image. This offers an efficient way of leveraging multi-level semantic information to achieve more accurate segmentation. Extensive experiments on three benchmarks demonstrate that the proposed DAN achieves the new state-of-the-art performance, surpassing the previous methods by large margins. The thorough ablation studies further reveal its great effectiveness for few-shot semantic segmentation. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

Collaborative Perception Datasets for Autonomous Driving: A Review

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Naibang Shang, Deyong Gong, Yan Hu, Xiaoxi Song, Ziying Yang, Lei Huang, Yuhan Wang, Xiaoyu Lu, Jianli Beijing100083 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China State Key Laboratory of Intelligent Green Vehicle and Mobility Tsinghua University Beijing100084 China Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence School of Computer Science and Technology Beijing Jiaotong University China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore School of Mechatronics Engineering Harbin Institute of Technology 92 West Dazhi St. Harbin China Department of Electronic & Electrical Engineering University of Bath United Kingdom

Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://***/frankwnb/Collaborative-Perceptio n-Datasets-for-Autonomous-Driving. © 2025, CC BY-SA.

关键词： Sensor data fusion

A sludge volume index (SVI) model based on the multivariate local quadratic polynomial regression method

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2018年第5期26卷 1071-1077页

作者： Honggui Han Xiaolong Wu Luming Ge Junfei Qiao College of Automation Faculty of Information Technology Beijing University of Technology Beijing 100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124 China

In this study, a multivariate local quadratic polynomial regression(MLQPR) method is proposed to design a model for the sludge volume index(SVI). In MLQPR, a quadratic polynomial regression function is established to describe the relationship between SVI and the relative variables, and the important terms of the quadratic polynomial regression function are determined by the significant test of the corresponding coefficients. Moreover, a local estimation method is introduced to adjust the weights of the quadratic polynomial regression function to improve the model accuracy. Finally, the proposed method is applied to predict the SVI values in a real wastewater treatment process(WWTP). The experimental results demonstrate that the proposed MLQPR method has faster testing speed and more accurate results than some existing methods.

关键词： Sludge volume index Multivariate quadratic polynomial regression Local estimation method Wastewater treatment process

MedSteGAN: Medical Embedding-Optimized Steganography with Improved GAN

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Peng, Yuxiang Fu, Chong Zheng, Yu Tian, Yunjia Cao, Guixing Chen, Junxin School of Computer Science and Engineering Northeastern University Liaoning Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang110819 China Department of Information Engineering The Chinese University of Hong Kong Ma Liu Shui Shatin New Territories Hong Kong Institute of Telecommunication Satellite China Academy of Space Technology Beijing100094 China School of Software Dalian University of Technology Liaoning Dalian116621 China

Medical diagnosing systems contain sensitive information, especially the resulting certificate of diagnosis that involves the patient’s privacy, required to be protected carefully. An effective way is to secretly embed privacy-sensitive information into medical-generated images, eventually being viewed as arbitrary images of nobody/nothing in public. The current research line of medical steganography targets simple data-hiding methods, yet remains barren in optimal embedding and stronger robustness. To fill this gap, we propose an end-to-end steganographic framework for medical images. Our idea is to integrate medical-image adaptive steganography with a generative adversarial network (GAN), named MedSteGAN. To improve both robustness, we design an optimized U-shape gen- erator that extracts features more efficiently utilizing larger kernel convolutions and the ReLU6 function. Also, deconvolutions are replaced by upsampling and convolution layers to avoid the checkerboard effect. To enhance security and image quality, we employ visual quality loss and mean squared error (MSE) loss based on the multi-scale structural similarity index metric (MS- SSIM) and the high-pass filters, respectively. Extensive experiments demonstrate that MedSteGAN outperforms state-of-the-art steganographic schemes in terms of robustness and image quality. © 2023, The Authors. All rights reserved.

关键词： Image quality

Poisoning attack against estimating from pairwise comparisons

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Big Data Mining and Knowledge Management The School of Economics and Management University of Chinese Academy of Sciences Beijing100049 China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically. © 2021, CC BY-NC-ND.

关键词： Toys

Numerical Simulation Method of Municipal Solid Waste Incineration Process Based on Grate Furnace: A Survey

学校读者我要写书评

暂无评论

Numerical Simulation Method of Municipal Solid Waste Inciner...

第三十九届中国控制会议

作者： Jiabin Zhuang Jian Tang Mingying Jia Hongjun Zhu Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System 55th Institute Joint staff of the Central Military Commission PLA Navy

The incineration process for municipal solid waste(MSW) has the advantages of fast speed, in-situ treatment, high capacity reduction rate, and energy recyclability. Among them, the MSW incineration(MSWI) based on mechanical grate furnaces is widely used. However, the diversity of MSW components and living habits, and the time-varying characteristic due to differences of natural environment, and frequent fluctuations in incineration conditions due to operating differences and equipment failures, etc., making it difficult to maintain the MSWI process operation at optimization status. Moreover, it is difficult to detect the combustion conditions in the furnace in real time by experimental methods and to verify the optimized control algorithm developed offline in terms of ensuring the safety of MSWI process. Thus, it is very important to construct a numerical simulation model of MSWI process close to actual operating conditions. Aim at the above problems, this paper reviews the numerical simulation method of MSWI process based on grate furnace. First, the MSWI process is described. Then, the numerical simulation methods of the MSWI process based on commercial software and self-developed software are summarized, and the advantages and disadvantages of each method are pointed out. Then, a comparative analysis of the above methods is given, and the difficulties are given out. Finally, the current status of numerical simulation is summarized, and future research directions and development prospects are given.

关键词： Grate furnace municipal solid waste incineration(MSWI) numerical simulation optimal control

LSTM Learn Policy from Dynamical system of Demonstration Motions for Robot Imitation Learning

学校读者我要写书评

暂无评论

LSTM Learn Policy from Dynamical System of Demonstration Mot...

IEEE International Conference on Cyber Technology in Automation, Control, and intelligent systems

作者： Jianjun Yu Hongke Yao Guoyu Zuo Shuo An Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Robot imitation learning has recently been studied extensively. There have been many methods for robot imitation learning. The main problem, however, is that the learned strategy is susceptible to external interference and thus deviates from the expected trajectory. In this paper we propose a method for robot learning human motion that combines the strengths of LSTM and dynamical system. Such an approach can learn policy effectively from dynamical system of motions while robot interacting with human demonstrators or other teachers. And this method effectively improves the ability of robot trajectory adjustment. Simulation experiments show that the proposed method which learn policy can effectively avoid the disturbance in the robot working environment.

关键词： Robots Trajectory Mathematical model Logic gates Time series analysis Task analysis

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Du, Yiyang Wang, Xiaochen Chen, Chi Ye, Jiabo Wang, Yiru Li, Peng Yan, Ming Zhang, Ji Huang, Fei Sui, Zhifang Sun, Maosong Liu, Yang Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Tsinghua University Beijing China State Key Laboratory of Multimedia Information Processing Peking University Beijing China School of Software Microelectronics Peking University Beijing China Institute of Intelligent Computing Alibaba Group China Shanghai Artificial Intelligence Laboratory Shanghai China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China ModelTC Open Source Organization Beijing China

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with identical architecture, they meet challenges when dealing with Multimodal Large Language Models (MLLMs) with inherent heterogeneous property, including differences in model architecture and the asymmetry in the parameter space. In this work, we propose AdaMMS1, a novel model merging method tailored for heterogeneous MLLMs. Our method tackles the challenges in three steps: mapping, merging and searching. Specifically, we first design mapping function between models to apply model merging on MLLMs with different architecture. Then we apply linear interpolation on model weights to actively adapt the asymmetry in the heterogeneous MLLMs. Finally in the hyper-parameter searching step, we propose an unsupervised hyper-parameter selection method for model merging. As the first model merging method capable of merging heterogeneous MLLMs without labeled data, extensive experiments on various model combinations demonstrated that AdaMMS outperforms previous model merging methods on various vision-language benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词：