79,981 Hits in 5.5 sec

Scalable Active Learning for Object Detection [article]

Elmar Haussmann, Michele Fenzi, Kashyap Chitta, Jan Ivanecky, Hanson Xu, Donna Roy, Akshita Mittel, Nicolas Koumchatzky, Clement Farabet, Jose M. Alvarez
2020 arXiv   pre-print
We have built a scalable production system for active learning in the domain of autonomous driving.  ...  Active learning is a powerful technique to improve data efficiency for supervised learning methods, as it aims at selecting the smallest possible training set to reach a required performance.  ...  In this paper, we described our scalable production system for active learning for object detection.  ... 
arXiv:2004.04699v1 fatcat:yvg7sy2zcvasxfmrcel7mn5kjy

Towards Dynamic and Scalable Active Learning with Neural Architecture Adaption for Object Detection

Fuhui Tang, Chenhan Jiang, Dafeng Wei, Hang Xu, Andi Zhang, Wei Zhang, Hongtao Lu, Chunjing Xu
2021 British Machine Vision Conference  
To overcome these problems, we propose a novel active learning strategy with dynamic neural architecture adaption for object detection.  ...  However, current active learning methods for object detection have three drawbacks: a) the network architectures of the detector during active learning are fixed without considering its saturation; (b)  ...  To overcome these problems, we propose dynamic and scalable active learning with neural architecture adaption for object detection.  ... 
dblp:conf/bmvc/TangJWXZ0LX21 fatcat:mfmzx3gdmrdc7dqlyv6zfgouz4

A General Active-Learning Framework for On-Road Vehicle Recognition and Tracking

Sayanan Sivaraman, Mohan Manubhai Trivedi
2010 IEEE transactions on intelligent transportation systems (Print)  
This paper introduces a general active-learning framework for robust on-road vehicle recognition and tracking.  ...  Using the query and archiving interface for active learning (QUAIL), the passively trained vehicle-recognition system is evaluated on an independent real-world data set, and informative samples are queried  ...  Murphy-Chutorian for their valuable contributions to testbed design and data collection. The authors would also like to thank the associate editor and reviewers for their valuable comments.  ... 
doi:10.1109/tits.2010.2040177 fatcat:ulb2peya3zdpzlu2ztu7m34kei

Educational scalability in MOOCs: Analysing instructional designs to find best practices

Kasch Julia, Van Rosmalen Peter, Kalz Marco
2020 Computers & Education  
The analysis indicated scalable best practices on various complexity levels and across different learning activities.  ...  A selection of design examples is discussed as potentially best practices for educational scalability, not only for MOOCs but also for online education in general.  ...  Acknowledgement This work is financed via a grant by the Dutch National Initiative for Education Research (NRO)/The Netherlands Organisation for Scientific Research (NWO) and the Dutch Ministry of Education  ... 
doi:10.1016/j.compedu.2020.104054 fatcat:m4y4mauksnaqjpplnmbkgqfw2i

A scalable FPGA based accelerator for Tiny-YOLO-v2 using OpenCL

Yap June Wai, Zulkanain Mohd Yussof, Sani Irwan Md Salim
2019 International Journal of Reconfigurable and Embedded Systems (IJRES)  
To best of our knowledge, this is the first implementation of Tiny-YOLO-v2 CNN based object detection algorithm on a small scale De1SoC board using Intel FPGA SDK for OpenCL approach.  ...  Deep Convolution Neural Network (CNN) algorithm have recently gained popularity in many applications such as image classification, video analytic, object recognition and segmentation.  ...  ACKNOWLEDGEMENTS Authors would like to thank Universiti Teknikal Malaysia Melaka (UTeM) and SKIM Zamalah for supporting this research  ... 
doi:10.11591/ijres.v8.i3.pp206-214 fatcat:7s7c3wub3zayvl42h2zxlmhxda

Scalable Security Analytics Framework Using NoSQL Database

Rizwan ur Rahman, Deepak Singh Tomar
2017 International Journal of Database Theory and Application  
Supervised and unsupervised learning techniques are applied for analytics on data collected from live application and experimental set-up.  ...  In this paper the scalable framework for security analytics is proposed using MongoDB NoSQL database. An attack scenario is created to simulate the zero-day malware.  ...  Researchers in [9] build up scalable quasi-real-time intrusion detection system. It is used to detect Peer-to-Peer Botnet attacks using machine learning approaches.  ... 
doi:10.14257/ijdta.2017.10.11.03 fatcat:kqyb77wei5cmljwy5fac3b74l4

Scalable object detection by filter compression with regularized sparse coding

Ting-Hsuan Chao, Yen-Liang Lin, Yin-Hsi Kuo, Winston H. Hsu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Many successful object detection systems use part-based model which trains several filters (classifiers) for each class to perform multiclass object detection.  ...  For practical applications, an object detection system requires huge number of classes to meet real world needs.  ...  We question that if sparse coding is still suitable for scalable object detection when the number of classes grows in the ILSVRC 2013 detection task.  ... 
doi:10.1109/cvpr.2015.7299015 dblp:conf/cvpr/ChaoLKH15 fatcat:gndcrq6q55cchgda6d7va7hpda

Big Data Scalability Issues in WAAS

Jan Prokaj, Xuemei Zhao, Jongmoo Choi, Gerard Medioni
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
We have designed and implemented a full system to detect and track vehicles, and infer activities.  ...  We address here the scalability issues, and propose solutions to have the tracker run in real time using different parallelism strategies.  ...  Given a detected object in one frame, we know there must be another detected instance of that object located nearby in subsequent frames.  ... 
doi:10.1109/cvprw.2013.67 dblp:conf/cvpr/ProkajZCM13 fatcat:2cmc4ct5xjggphjp26sboyq2za

2020 Index IEEE Open Journal of Signal Processing Vol. 1

2020 IEEE Open Journal of Signal Processing  
., +, OJSP 2020 1-13 O Object detection Masked-RPCA: Moving Object Detection With an Overlaying Model.  ...  ., +, OJSP 2020 146-158 + Check author entry for coauthors Image sequences Masked-RPCA: Moving Object Detection With an Overlaying Model.  ... 
doi:10.1109/ojsp.2021.3053848 fatcat:23vjqfgxf5efjbgsc2mqni5m6m

Towards a Scalable and Adaptive Learning Approach for Network Intrusion Detection

Alebachew Chiche, Million Meshesha, Rui Zhang
2021 Journal of Computer Networks and Communications  
This paper introduces a new integrated learning approach towards developing a new network intrusion detection model that is scalable and adaptive nature of learning.  ...  Interestingly, significant knowledge rich learning for intrusion detection differs as a fundamental feature of intrusion detection and prevention techniques.  ...  However, there is no attempt to design scalable and adaptive learning approach for intrusion detection.  ... 
doi:10.1155/2021/8845540 fatcat:t2k3ryspbbglrns3z427nrm4xq

TAILOR: Teaching with Active and Incremental Learning for Object Registration [article]

Qianli Xu, Nicolas Gauthier, Wenyu Liang, Fen Fang, Hui Li Tan, Ying Sun, Yan Wu, Liyuan Li, Joo-Hwee Lim
2022 arXiv   pre-print
We present TAILOR -- a method and system for object registration with active and incremental learning.  ...  learning algorithm to learn new objects without potential forgetting of previously learned objects.  ...  Acknowledgments This research is supported by the Agency for Science, Technology and Research (A*STAR) under AME Programmatic Funding Scheme (Project No. A18A2b0046).  ... 
arXiv:2205.11692v1 fatcat:uhck3mhuofbezgfst2ckt2nesq

Autonomous Generation of Internal Representations for Associative Learning [chapter]

Michaël Garcia Ortiz, Benjamin Dittes, Jannik Fritsch, Alexander Gepperth
2010 Lecture Notes in Computer Science  
for system-level learning.  ...  We formulate requirements for performing systemlevel learning (online operation, scalability to high-dimensional inputs, data mining ability, generality and simplicity) and present a suitable neural learning  ...  The motivation for this study arose when trying to obtain multimodal object models (in this case: car models) for excluding obviously incorrect object detections.  ... 
doi:10.1007/978-3-642-15825-4_30 fatcat:sxnqjxba4zcqnjokplk43jyid4

IoT Driven Ambient Intelligence Architecture for Indoor Intelligent Mobility

Varuna De Silva, Jamie Roche, Xiyu Shi, Ahmet Kondoz
2018 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech)  
Our objective is to utilize sensors in home settings in the least invasive manner for the robot to learn about its dynamic surroundings and interact in a human-like manner.  ...  Towards addressing the above problems, in this paper we present an architecture for "Ambient Intelligence" for indoor intelligent mobility by leveraging IoTs within a framework of Scalable Multi-layered  ...  To overcome the need for dedicated hardware and firmware updates, [25] proposed an activity recognition system by learning the received signal strength indicator (RSSI) fingerprint of six different activities  ... 
doi:10.1109/dasc/picom/datacom/cyberscitec.2018.00090 dblp:conf/dasc/SilvaRSK18 fatcat:2bpu3u4owvg37h5rvflcakcitu

Scalable Surveillance Software Architecture

Henry Detmold, Anthony Dick, Katrina Falkner, David Munro, Anton Den Hengel, Ron Morrison
2006 2006 IEEE International Conference on Video and Signal Based Surveillance  
Video surveillance is a key technology for enhanced protection of facilities such as airports and power stations from various types of threat.  ...  A novel architecture for video surveillance is presented, and its efficacy demonstrated through application to an important class of surveillance algorithms.  ...  The single scene analysis level derives hypotheses like "left luggage" from activity and detection of particular objects via signatures.  ... 
doi:10.1109/avss.2006.101 dblp:conf/avss/DetmoldDFMHM06 fatcat:cc636wvx25hmnjob5b5jvnciou

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

Honglak Lee, Roger Grosse, Rajesh Ranganath, Andrew Y. Ng
2009 Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09  
Our experiments show that the algorithm learns useful high-level visual features, such as object parts, from unlabeled images of objects and natural scenes.  ...  There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks.  ...  Acknowledgment We give warm thanks to Daniel Oblinger and Rajat Raina for helpful discussions. This work was supported by the DARPA transfer learning program under contract number FA8750-05-2-0249.  ... 
doi:10.1145/1553374.1553453 dblp:conf/icml/LeeGRN09 fatcat:d2ca2l6x5jfixj57qbw7wp4zzq
« Previous Showing results 1 — 15 out of 79,981 results