检索结果-内蒙古大学图书馆

Complementary Labels Learning with Augmented Classes

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Li, Zhongnian Xu, Mengting Xu, Xinzheng Zhang, Daoqiang School of Computer Science and Technology China University of Ming and Technogy Jiangsu Xuzhou221000 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing210000 China College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310000 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing210000 China

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised ***, most previous CLL algorithms were in a stable environment rather than an open and dynamic scenarios, where data collected from unseen augmented classes in the training process might emerge in the testing *** this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase. Specifically, by using unlabeled data, we propose an unbiased estimator of classification risk for CLLAC, which is guaranteed to be provably consistent. Moreover, we provide generalization error bound for proposed method which shows that the optimal parametric convergence rate is achieved for estimation error. Finally, the experimental results on several benchmark datasets verify the effectiveness of the proposed method. © 2023, The Authors. All rights reserved.

关键词： machine learning

Formal modeling and performance evaluation for hybrid systems: A probabilistic hybrid process algebra-based approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Fujun J. Cao, Zining Tan, Lixing Li, Zhen College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Electro-optic Control Laboratory Luoyang China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

Probabilistic behavior is omnipresent in computer controlled systems, in particular, so-called safety-critical hybrid systems, because of various reasons, like uncertain environments, or fundamental properties of nature. In this paper, we extend existing hybrid process algebra ACPsrths with probability without replacing nondeterministic choice operator. In view of some shortcomings in existing approximate probabilistic bisimulation, we relax the constrains and propose a novel approximate probabilistic bisimulation relation. After that, we present a performance evaluation language CTRML, to reason over probabilistic systems, which extend the results to real number. Along with the specification language, we present a set of algorithms for the evaluation of the language. Additionally, we transfer the hybrid process algebra to probabilistic transition system and show experimental results. Copyright © 2020, The Authors. All rights reserved.

关键词： Hybrid systems

Rate-Distortion Modeling for Bit Rate Constrained Point Cloud Compression

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Pan Luo, Shengzhou Paul, Manoranjan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing211106 China School of Software South China Normal University Foshan528225 China School of Computing and Mathematics Charles Sturt University BathurstNSW2795 Australia

As being one of the main representation formats of 3D real world and well-suited for virtual reality and augmented reality applications, point clouds have gained a lot of popularity. In order to reduce the huge amount of data, a considerable amount of research on point cloud compression has been done. However, given a target bit rate, how to properly choose the color and geometry quantization parameters for compressing point clouds is still an open issue. In this paper, we propose a rate-distortion model based quantization parameter selection scheme for bit rate constrained point cloud compression. Firstly, to overcome the measurement uncertainty in evaluating the distortion of the point clouds, we propose a unified model to combine the geometry distortion and color distortion. In this model, we take into account the correlation between geometry and color variables of point clouds and derive a dimensionless quantity to represent the overall quality degradation. Then, we derive the relationships of overall distortion and bit rate with the quantization parameters. Finally, we formulate the bit rate constrained point cloud compression as a constrained minimization problem using the derived polynomial models and deduce the solution via an iterative numerical method. Experimental results show that the proposed algorithm can achieve optimal decoded point cloud quality at various target bit rates, and substantially outperform the video-rate-distortion model based point cloud compression scheme. Copyright © 2022, The Authors. All rights reserved.

关键词： Lagrange multipliers

Complementary Labels Learning with Augmented Classes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zhongnian Zhang, Jian Xu, Mengting Xu, Xinzheng Zhang, Daoqiang School of Computer Science and Technology China University of Ming and Technogy Jiangsu Xuzhou221000 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing210000 China college of computer science and technology Zhejiang University Zhejiang Hangzhou310000 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing210000 China

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most previous CLL algorithms were in a stable environment rather than an open and dynamic scenarios, where data collected from unseen augmented classes in the training process might emerge in the testing phase. In this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase. Specifically, by using unlabeled data, we propose an unbiased estimator of classification risk for CLLAC, which is guaranteed to be provably consistent. Moreover, we provide generalization error bound for proposed method which shows that the optimal parametric convergence rate is achieved for estimation error. Finally, the experimental results on several benchmark datasets verify the effectiveness of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

Learning from Positive and Unlabeled Data with Augmented Classes

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Li, Zhongnian Yang, Liutao Ma, Zhongchen Sun, Tongfeng Xu, Xinzheng Zhang, Daoqiang School of Computer Science and Technology China University of Ming and Technogy Jiangsu Xuzhou221000 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing210000 China School of Computer Science and communications Engineering Jiangsu University Jiangsu Zhenjiang212013 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing210000 China

Positive Unlabeled (PU) learning aims to learn a binary classifier from only positive and unlabeled data, which is utilized in many real-world scenarios. However, existing PU learning algorithms cannot deal with the real-world challenge in an open and changing scenario, where examples from unobserved augmented classes may emerge in the testing phase. In this paper, we propose an unbiased risk estimator for PU learning with Augmented Classes (PUAC) by utilizing unlabeled data from the augmented classes distribution, which can be easily collected in many real-world scenarios. Besides, we derive the estimation error bound for the proposed estimator, which provides a theoretical guarantee for its convergence to the optimal solution. Experiments on multiple realistic datasets demonstrate the effectiveness of proposed approach. © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Learning from Positive and Unlabeled Data with Augmented Classes

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

关键词： Learning algorithms

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Haoran Chen, Honghua Zhang, Yingkui Wei, Mingqiang Xie, Haoran Wang, Jun Lu, Tong Qin, Jing Zhang, Xiao-Ping State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Department of Computing and Decision Sciences Lingnan University Hong Kong School of Nursing The Hong Kong Polytechnic University Hong Kong Department of Electrical Computer and Biomedical Engineering Ryerson University Toronto Canada

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets. Our code is available at https://***/hrzhou2/refinenet. Copyright © 2022, The Authors. All rights reserved.

关键词： Domain Knowledge

Learning Calibrated-Guidance for Object Detection in Aerial Images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wei, Zongqi Liang, Dong Zhang, Dong Zhang, Liyan Geng, Qixiang Wei, Mingqiang Zhou, Huiyu The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The School of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

Object detection is one of the most fundamental yet challenging research topics in the domain of computer vision. Recently, the study on this topic in aerial images has made tremendous progress. However, complex background and worse imaging quality are obvious problems in aerial object detection. Most state-of-the-art approaches tend to develop elaborate attention mechanisms for the space-time feature calibrations with arduous computational complexity, while surprisingly ignoring the importance of feature calibrations in channel-wise. In this work, we propose a simple yet effective Calibrated-Guidance (CG) scheme to enhance channel communications in a feature transformer fashion, which can adaptively determine the calibration weights for each channel based on the global feature affinity correlations. Specifically, for a given set of feature maps, CG first computes the feature similarity between each channel and the remaining channels as the intermediary calibration guidance. Then, re-representing each channel by aggregating all the channels weighted together via the guidance operation. Our CG is a general module that can be plugged into any deep neural networks, which is named as CG-Net. To demonstrate its effectiveness and efficiency, extensive experiments are carried out on both oriented object detection task and horizontal object detection task in aerial images. Experimental results on two challenging benchmarks (i.e., DOTA and HRSC2016) demonstrate that our CG-Net can achieve the new state-of-the-art performance in accuracy with a fair computational overhead. The source code has been open sourced at https://***/WeiZongqi/CG-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Object recognition

A rough set approach for planner evaluation

学校读者我要写书评

暂无评论

A rough set approach for planner evaluation

IEEE International Conference on Systems, Man and Cybernetics

作者： B.K. Sy Wang Jiaxin Pattern Analysis and Machine Intelligence Group System Design Engineering Department University of Waterloo Waterloo ONT Canada Department of Computer Science CUNY Flushing NY USA The State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper discusses a rough set approach for evaluating solutions of scheduling problems. Algorithms for solving scheduling problems are planners and the scheduling problems are modelled as constraint satisfaction problems. Conventional approach for the analysis of algorithms often focuses on the time and representational complexities, and assumes an identical cost on all operations. The proposed rough set approach augments conventional approaches for the analysis of algorithms in two ways: 1) it permits the consideration of different costs arising from different operations; and 2) it allows one to define a new utility for a complexity analysis.

关键词： Algorithm design and analysis Processor scheduling Set theory machine intelligence Computer science Costs Search problems Educational institutions pattern analysis System analysis and design