483 Hits in 3.1 sec

Semisupervised Clustering by Queries and Locally Encodable Source Coding [article]

Arya Mazumdar, Soumyabrata Pal
2020 arXiv   pre-print
In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding.  ...  Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input.  ...  Semisupervised Clustering by Queries and Locally Encodable Source Coding Arya Mazumdar Senior Member, IEEE, Soumyabrata Pal Abstract-Source coding is the canonical problem of data compression in information  ... 
arXiv:1904.00507v2 fatcat:ngogbnouenfvtk5i5d3572bxj4

Learning to Hash for Indexing Big Data—A Survey

Jun Wang, Wei Liu, Sanjiv Kumar, Shih-Fu Chang
2016 Proceedings of the IEEE  
We provide a comprehensive survey of the learning-to-hash framework and representative techniques of various types, including unsupervised, semisupervised, and supervised.  ...  In many critical applications such as largescale search and pattern matching, finding the nearest neighbors to a query is a fundamental research problem.  ...  [19] , asymmetric binary embedding [20] , kernel methods [21] , [22] , compressed sensing [23] , maximum margin learning [24] , sequential learning [25] , clustering analysis [26] , semisupervised  ... 
doi:10.1109/jproc.2015.2487976 fatcat:4eok2ubzxnc5nmc4hgt4qmqhcy

IEEE Access Special Section Editorial: Advanced Data Mining Methods for Social Computing

Yongqiang Zhao, Shirui Pan, Jia Wu, Huaiyu Wan, Huizhi Liang, Haishuai Wang, Huawei Shen
2020 IEEE Access  
YONGQIANG ZHAO (Member, IEEE) received the B.S. degree in automation and the M.S. and Ph.D. degrees in control theory and control engineering from Northwestern  ...  an efficient incremental semisupervised classification method named CODES (Classification Over Drifting and Evolving Stream).  ...  The article by Bi et al., ''CODES: Efficient incremental semisupervised classification over drifting and evolving social streams,'' addresses the major challenges of social stream classification by proposing  ... 
doi:10.1109/access.2020.3043060 fatcat:qbqk5f4ojvadlazhk2mc343sra

Hashing Techniques

Lianhua Chi, Xingquan Zhu
2017 ACM Computing Surveys  
Hashing techniques have also evolved from simple randomization approaches to advanced adaptive methods considering locality, structure, label information, and data security, for effective hashing.  ...  With the rapid development of information storage and networking technologies, quintillion bytes of data are generated every day from social networks, business transactions, sensors, and many other domains  ...  For verification purposes, the software owner can publish the MD5 [Rivest 1992 ] hash code of the software. Users can download software from different sources and generate a new MD5 code.  ... 
doi:10.1145/3047307 fatcat:u5asusjs7vdq7f3a6wgnesnodq

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification [article]

Yang Fu, Yunchao Wei, Guanshuo Wang, Yuqian Zhou, Honghui Shi, Thomas Huang
2019 arXiv   pre-print
Concretely, we propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from global body to local parts) of unlabeled samples to automatically build multiple clusters  ...  Without spending much effort on labeling, our SSG ++ can further promote the mAP upon SSG by 10.7% and 6.9%, respectively. Our Code is available at: .  ...  Acknowledgements: This work is part supported by IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR) and ARC DECRA DE190101315.  ... 
arXiv:1811.10144v3 fatcat:wjvajgjvsjctjpo45nmouqiifa

Supporting AI Engineering on the IoT Edge through Model-Driven TinyML [article]

Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann
2022 arXiv   pre-print
Software engineering of network-centric Artificial Intelligence (AI) and Internet of Things (IoT) enabled Cyber-Physical Systems (CPS) and services, involves complex design and validation challenges.  ...  We focus on a sub-discipline of AI, namely Machine Learning (ML) and propose the delegation of data analytics and ML to the IoT edge.  ...  The authors would like to also thank Stephan Rössler from Software AG and Marouane Sayih (alumnus of the Technical University of Munich) for their collaboration and support.  ... 
arXiv:2107.02690v2 fatcat:3yuy6b67cne4zmohlmh6rmsxdm

Contrastive Representation Learning: A Framework and Review [article]

Phuc H. Le-Khac, Graham Healy, Alan F. Smeaton
2020 arXiv   pre-print
However, the origins of Contrastive Learning date as far back as the 1990s and its development has spanned across many fields and domains including Metric Learning and natural language processing.  ...  In this paper we provide a comprehensive literature review and we propose a general Contrastive Representation Learning framework that simplifies and unifies many different contrastive learning methods  ...  The color for defining similarity in query and keys encodes: Multi-sensory, Data transformation, Context-Instance, Sequential Coherence, Clustering.  ... 
arXiv:2010.05113v1 fatcat:xdegcaoarvevdfl4r22pyzqr4e

Deep Hashing for Semi-supervised Content Based Image Retrieval

2018 KSII Transactions on Internet and Information Systems  
Proposed activation and loss functions helped to minimize classification error and produce better hash codes.  ...  Proposed approach uses semi-supervised deep hashing with semantic learning and binary code generation by minimizing the objective function.  ...  Semisupervised tag hashing (SSTH) [35] performed supervised learning with class labels and hash codes while unsupervised learning between input images.  ... 
doi:10.3837/tiis.2018.08.013 fatcat:lessznvvsva65ip743jbfu425q

Contrastive Representation Learning: A Framework and Review

Phuc H. Le-Khac, Graham Healy, Alan F. Smeaton
2020 IEEE Access  
Science Foundation Ireland through the SFI Centre for Research Training in Machine Learning (18/CRT/6183) and the Insight Centre for Data Analytics (SFI/12/RC/2289_P2).  ...  The color for defining similarity in query and keys encodes: Multi-sensory, Data transformation, Context-Instance, Sequential Coherence, Clustering.  ...  The color for defining similarity in query and keys encodes: Multi-sensory, Data transformation, Context-Instance, Sequential Coherence, Clustering.  ... 
doi:10.1109/access.2020.3031549 fatcat:qohhn2f2tray5ha3iafxbnwp74

Vehicle Re-Identification Based on Complementary Features [article]

Cunyuan Gao, Yi Hu, Yi Zhang, Rui Yao, Yong Zhou, Jiaqi Zhao
2020 arXiv   pre-print
The codes are available at  ...  Due to the vehicle's orientation, lighting and inter-class similarity, it is difficult to achieve robust and discriminative representation feature.  ...  [29] and Guo et al. [4] seek a better feature encoding method.  ... 
arXiv:2005.04463v1 fatcat:bunl4ccv2zacvhymnmpbn2i2mi

Locality-Sensitive Hashing Techniques for Nearest Neighbor Search

Keon Myung Lee
2012 International Journal of Fuzzy Logic and Intelligent Systems  
This paper introduces the notion of locality-sensitive hashing and surveys the locality-sensitive hashing techniques.  ...  Nearest neighbor search is such a task which finds from a data set the k nearest data points to queries.  ...  [16] are defined as follows: First, data points are encoded into binary codes in the Hamming space.  ... 
doi:10.5391/ijfis.2012.12.4.300 fatcat:qwkw27hpd5ht5jhzwfgcajyfs4

Applications of Multi-view Learning Approaches for Software Comprehension

Amir Saeidi, Jurriaan Hage, Ravi Khadka, Slinger Jansen
2019 The Art, Science, and Engineering of Programming  
high-level units and give component-level recommendations for refactoring of the system, as well as cross-view source code search.  ...  A software system consists of various views including the module dependency graph, execution logs, evolutionary information and the vocabulary used in the source code, that collectively defines the software  ...  The similarity between a query and a source code unit is defined based on their textual feature vectors.  ... 
doi:10.22152/ fatcat:5bw467krprefzdhw7nvu4ib3wm

Application of Convolutional Neural Networks for Stellar Spectral Classification

Kaushal Sharma, Ajit Kembhavi, Aniruddha Kembhavi, T Sivarani, Sheelu Abraham, Kaustubh Vaghmare
2019 Monthly notices of the Royal Astronomical Society  
to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H].  ...  , ELODIE and MILES spectral libraries as training samples.  ...  We thank the anonymous referee for the careful review and suggestions that significantly improved the quality of this work. In this work, we have extensively used SDSS data base.  ... 
doi:10.1093/mnras/stz3100 fatcat:7cgunurcffdqtm34nxvzer3f6y

A Survey on Deep Hashing Methods

Xiao Luo, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, Xian-Sheng Hua
2022 ACM Transactions on Knowledge Discovery from Data  
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining  ...  , we categorize deep supervised hashing methods into pairwise methods, ranking-based methods, pointwise methods as well as quantization according to how measuring the similarities of the learned hash codes  ...  We also thank Zeyu Ma, Huasong Zhong and Xiaokang Chen who discussed with us and provided instructive suggestions.  ... 
doi:10.1145/3532624 fatcat:7lxtu2qzvvhrpnjngefli2mvca

A Survey on Visual Content-Based Video Indexing and Retrieval

Weiming Hu, Nianhua Xie, Li Li, Xianglin Zeng, S. Maybank
2011 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
retrieval including query interfaces, similarity measure and relevance feedback, and video browsing.  ...  This paper offers a tutorial and an overview of the landscape of general strategies in visual content-based video indexing and retrieval, focusing on methods for video structure analysis, including shot  ...  Query descriptions are enriched from knowledge sources, such as ontology of concepts or keywords. Snoek et al.  ... 
doi:10.1109/tsmcc.2011.2109710 fatcat:qtenus4htffcfbyuiwidgjojku
« Previous Showing results 1 — 15 out of 483 results