检索结果-内蒙古大学图书馆

On efficient and robust metrics for RANSAC hypotheses and 3D rigid registration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Jiaqi Huang, Zhiqiang Quan, Siwen Zhang, Qian Zhang, Yanning Cao, Zhiguo National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China School of Software Northwestern Polytechnical University Xi’an710129 China School of Electronic and Control Engineering Chang’an University Xi’an710064 China School of Resources and Environment Hubei University Wuhan430062 China National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration. Estimating six-degree-of-freedom (6-DoF) pose from feature correspondences remains a popular approach to 3D rigid registration, where random sample consensus (RANSAC) is a de-facto choice to this problem. However, existing metrics for RANSAC hypotheses are either time-consuming or sensitive to common nuisances, parameter variations, and different application scenarios, resulting in performance deterioration in overall registration accuracy and speed. We alleviate this problem by first analyzing the contributions of inliers and outliers, and then proposing several efficient and robust metrics with different designing motivations for RANSAC hypotheses. Comparative experiments on four standard datasets with different nuisances and application scenarios verify that the proposed metrics can significantly improve the registration performance and are more robust than several state-of-the-art competitors, making them good gifts to practical applications. This work also draws an interesting conclusion, i.e., not all inliers are equal while all outliers should be equal, which may shed new light on this research problem. Copyright © 2020, The Authors. All rights reserved.

关键词： Deterioration

ICSTrace: A Malicious IP Traceback Model for Attacking Data of Industrial Control System

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xiao, Feng Xu, Qiang Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Electronic Engineering Institute of Hefei China

Considering the attacks against industrial control system are mostly organized and premeditated actions, IP traceback is significant for the security of industrial control system. Based on the infrastructure of the Internet, we have developed a novel malicious IP traceback model-ICSTrace, without deploying any new services. The model extracts the function codes and their parameters from the attack data according to the format of industrial control protocol, and employs a short sequence probability method to transform the function codes and their parameter into a vector, which characterizes the attack pattern of malicious IP addresses. Furthermore, a Partial Seeded K-Means algorithm is proposed for the pattern’s clustering, which helps in tracing the attacks back to an organization. ICSTrace is evaluated basing on the attack data captured by the large-scale deployed honeypots for industrial control system, and the results demonstrate that ICSTrace is effective on malicious IP traceback in industrial control system. Copyright © 2019, The Authors. All rights reserved.

关键词： K-means clustering

Improve the Performance of LSM-Tree based on Key-Value via Multithreading

学校读者我要写书评

暂无评论

Improve the Performance of LSM-Tree based on Key-Value via M...

International Symposium on Distributed Computing and applications to Business, engineering and science (DCABES)

作者： Yuan Gao Ping Xie Wendi Hua Meng Lv Jiating Lu College of Computer of Qinghai Normal University Xining P. R. China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining P. R. China Key Laboratory of Internet of Things of Qinghai Province Xining P. R. China Academy of Plateau Science and Sustainability Xining P. R. China School of Physical and Electrical Engineering Qinghai Normal University Xining P. R. China

ISBN: (纸本)9781665428903

In the era of big data, key-value storage systems based on Log-Structure Merge tree (LSM-tree) are widely used in numerous industries. LSM-Tree is divided into two parts, one part is in the memory and the other part is on the hard disk. When writing data, first write to the memory, when the Immutable Memtable in the memory is full of data, then write to the disk to output a Sorted String Table (SSTable) file. However, the use of writing data from memory to disk is single-threaded. When the Immutable Memtable writes data to the disk, it will block other threads. This article uses multiple Immutable Memtables and multi-threaded writing to solve the single-thread blocking problem. By running the benchmarks of LevelDB to analyze the experiment, the experimental results indicate a higher improvement.

关键词： Industries Multithreading Instruction sets Writing Big Data Benchmark testing Hard disks

Predicting Large-scale Protein-protein Interactions by Extracting Coevolutionary Patterns with MapReduce Paradigm

学校读者我要写书评

暂无评论

Predicting Large-scale Protein-protein Interactions by Extra...

IEEE International Conference on Systems, Man and Cybernetics

作者： Lun Hu Bo-Wei Zhao Shicheng Yang Xin Luo MengChu Zhou Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi China School of Computer Science and Technology Wuhan University of Technology Wuhan China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Hengrui (Chongqing) Artificial Intelligence Research Center Cloudwalk China New Jersey Institute of Technology Newark NJ USA

ISBN: (纸本)9781665442084

Protein-protein interactions are of great significance for us to understand the functional mechanisms of proteins. With the rapid development of high-throughput genomic technology, the amount of protein-protein interaction data has become so big that most of existing prediction algorithms are no longer applicable. To address this problem, we develop a distributed framework by reimplementing one of state-of-the-art algorithms, i.e., CoFex, by using MapReduce. In particular, we adopt a novel tree-based data structure to reduce the heavy memory consumption cased by the huge sequence information of proteins. After that, the procedure of CoFex is modified by following the paradigm of MapReduce such that the prediction task can be completed in a distributed manner, thus fulfilling the demanding requirements of large-scale protein-protein interaction prediction. A series of experiments have been conducted to evaluate the performance of the proposed distributed framework in terms of both efficiency and effectiveness. Experimental results demonstrate that the proposed framework can considerably improve the efficiency of CoFex by achieving more than two-orders-of-magnitude improvement in computational efficiency while retaining a comparable level of accuracy.

关键词： Proteins Memory management Genomics Predictive models Prediction algorithms Data structures Computational efficiency

Pairwise relation learning for semi-supervised gland segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xie, Yutong Zhang, Jianpeng Liao, Zhibin Shen, Chunhua Verjans, Johan Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xian710072 China University of Adelaide Australia South Australian Health and Medical Research Institute Adelaide Australia Research & Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Accurate and automated gland segmentation on histology tissue images is an essential but challenging task in the computer-aided diagnosis of adenocarcinoma. Despite their prevalence, deep learning models always require a myriad number of densely annotated training images, which are difficult to obtain due to extensive labor and associated expert costs related to histology image annotations. In this paper, we propose the pairwise relation-based semi-supervised (PRS2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net). The S-Net is trained on labeled data for segmentation, and PR-Net is trained on both labeled and unlabeled data in an unsupervised way to enhance its image representation ability via exploiting the semantic consistency between each pair of images in the feature space. Since both networks share their encoders, the image representation ability learned by PR-Net can be transferred to S-Net to improve its segmentation performance. We also design the object-level Dice loss to address the issues caused by touching glands and combine it with other two loss functions for S-Net. We evaluated our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset. Our results not only demonstrate the effectiveness of the proposed PR-Net and object-level Dice loss, but also indicate that our PRS2 model achieves the state-of-the-art gland segmentation performance on both benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： Histology

Discriminative and robust online learning for siamese visual tracking

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Jinghao Wang, Peng Sun, Haoyang School of Computer Science and School of Automation Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology

The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding space. Despite the recent success, each method agonizes over its intrinsic constraint. The online-only approaches suffer from a lack of generalization of the model they learn thus are inferior in target regression, while the offline-only approaches (e.g., convontional siamese trackers) lack the target-specific context information thus are not discriminative enough to handle distractors, and robust enough to deformation. Therefore, we propose an online module with an attention mechanism for offline siamese networks to extract target-specific features under L2 error. We further propose a filter update strategy adaptive to treacherous background noises for discriminative learning, and a template update strategy to handle large target deformations for robust learning. Validity can be validated in the consistent improvement over three siamese baselines: SiamFC, SiamRPN++, and SiamMask. Beyond that, our model based on SiamRPN++ obtains the best results over six popular tracking benchmarks and can operate beyond real-time. Copyright © 2019, The Authors. All rights reserved.

关键词： Deformation

A unified object motion and affinity model for online Multi-Object Tracking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yin, Junbo Wang, Wenguan Meng, Qinghao Yang, Ruigang Shen, Jianbing Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology China ETH Zurich Switzerland Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China Inception Institute of Artificial Intelligence United Arab Emirates University of Kentucky Kentucky United States

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant – requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

Is heuristic sampling necessary in training deep object detectors?

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Joya Liu, Dong Xu, Tong Wu, Shiwei Cheng, Yifei Chen, Enhong Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China School of Computer Science and Technology School of Data Science Department of Electronic Engineering and Information Science University of Science and Technology of China

To train accurate deep object detectors under the extreme foreground-background imbalance, heuristic sampling methods are always necessary, which either re-sample a subset of all training samples (hard sampling methods, e.g. biased sampling, OHEM), or use all training samples but re-weight them discriminatively (soft sampling methods, e.g. Focal Loss, GHM). In this paper, we challenge the necessity of such hard/soft sampling methods for training accurate deep object detectors. While previous studies have shown that training detectors without heuristic sampling methods would significantly degrade accuracy, we reveal that this degradation comes from an unreasonable classification gradient magnitude caused by the imbalance, rather than a lack of re-sampling/re-weighting. Motivated by our discovery, we propose a simple yet effective Sampling-Free mechanism to achieve a reasonable classification gradient magnitude by initialization and loss scaling. Unlike heuristic sampling methods with multiple hyperparameters, our Sampling-Free mechanism is fully data diagnostic, without laborious hyperparameters searching. We verify the effectiveness of our method in training anchor-based and anchor-free object detectors, where our method always achieves higher detection accuracy than heuristic sampling methods on COCO and PASCAL VOC datasets. Our Sampling-Free mechanism provides a new perspective to address the foreground-background imbalance. Our code is released at https://***/ChenJoya/sampling-free. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

A High-Gain Antenna with Dual Circular Polarization for W-band mmWave Wireless Communications

学校读者我要写书评

暂无评论

A High-Gain Antenna with Dual Circular Polarization for W-ba...

IEEE International Conference on Computing, Communications and IoT applications

作者： Chao Shu Shaoqing Hu Yuan Yao Xiaodong Chen School of Electronic Engineering and Computer Science Queen Mary University of London BUPT-QMUL EM Theory & Application International Research Lab School of Electronic Engineering Beijing University of Posts and Telecommunications

ISBN: (数字)9781728119731

ISBN: (纸本)9781728119748

This paper presents our study on an Axially Displaced Ellipse (ADE) reflector antenna fed by a dual circular polarized antenna, which is able to provide both high-gain and Full-Duplex capabilities for mmWave wireless communication systems. The feed is a horn antenna based on a stepped septum polarizer which can generate both Left Hand Circular Polarization (LHCP) and Right Hand Circular Polarization (RHCP). An ADE reflector antenna is also designed in order to provide high gain while keep a low reflection back to the feed, when two orthogonal circular polarized signals are transmitted and received at the same time to achieve Polarization-Division Multiplexing (PDM) or Full-Duplex in mmWave wireless communication systems. The simulation results show that the ADE reflector antenna system can achieve directivity of 50.3 dBic and SLL lower than -20 dB for both LHCP and RHCP at the center frequency.

关键词： Millimetre wave Dual circular polarization Axially displaced ellipse reflector millimeter wave high gain right hand circular polarization horn antennas center frequency Reflector antennas low-reflection ADE DAE protocol left hand circular polarization High-gain Antenna AXIAL directivity Wireless communication systems CIRCULAR POLARIZATION