Computer Science ›› 2016, Vol. 43 ›› Issue (12): 13-23.doi: 10.11896/j.issn.1002-137X.2016.12.003

Previous Articles     Next Articles

State-of-the-art on Deep Learning and its Application in Image Object Classification and Detection

LIU Dong, LI Su and CAO Zhi-dong   

  • Online:2018-12-01 Published:2018-12-01

Abstract: For traditional algorithms and strategies on image object classification and detection is hard to face the Challenges from efficiency,performance and intelligent of processing of image video big data.Based on the simulation of a hierarchical structure existing in human brain,deep learning can establish the mapping between the low-level signals and the high-level semantics for achieving the hierarchical expression of data characteristic.Deep learning with powerful ablility for visual information processing becomes the cutting-edge technology and research hot spot in coping with the coming challenge.At first,in this paper the basic theory of deep learning was discussed.Then,around image object classification and detection,we respectively summarized the development of deep learning in the visual field recentely.Finally,deep learning and its current problems in the visual field and the subsequent research direction were discussed in a well-informed level.

Key words: Deep learning,Feature representations,Image object classification,Image object detection

[1] Marr D.Vision:A Computational Investigation Into the HumanRepresentation and Processing of VisualInformation[M].Cambridge:The MIT Press,2010
[2] Huang Kai-qi,Ren Wei-qiang,Tan Tie-niu.Review on ImageObject Classification and Detection[J].Chinese Journal of Computers,2014,7(6):1225-1240(in Chinese) 黄凯奇,任伟强,谭铁牛.图像物体分类与检测算法综述[J].计算机学报,2014,7(6):1225-1240
[3] Karpathy A,Toderici G,Shetty S,et al.Large-Scale VideoClassification with Convolutional Neural Networks[C]∥IEEE Conference on CVPR.2014:1725-1732
[4] Sanchez-Riera J,Yuan-Sheng Hsiao,TekoingLim,et al.Arobust tracking algorithm for 3D hand gesture with rapidhandmotion through deep learning[C]∥IEEE Conference on Multimedia and Expo Workshops(ICMEW).2014:1-6
[5] Wikipedia.Computervision[EB/OL].
[6] Kong B.Comparison between human vision and computer vision [J].Nature Magazine,2002,4(1):51-55
[7] Statistical Report on the Development of the 38th China Internet Network,CNNIC[R/OL].[2016-08-03].
[8] Huang Kai-qi,Chen Xiao-tang,Tan Tie-niu,et al.IntelligentVisual Surveillance:A Review[J].Chinese Journal of Compu-ters,2015,38(6):1193-1118(in Chinese) 黄凯奇,陈晓棠,谭铁牛,等.智能视频监控技术综述[J].计算机学报,2015,38(6):1193-1118
[9] James J.Data NeverSleeps 2.0 [EB/OL].(2014-04-23)[2014-07-20].
[10] Dong Yu,Hinton G,Morgan N,et al.Introduction to the Special Section on Deep Learning for Speech and Language Processing[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,0(1):4-6
[11] Lee T,Mumford D.Hierarchical Bayesian inference in the visual cortex[J].JOSA A,2003,0(7):1434-1448
[12] Sun Zhi-yuan,Lu Cheng-xiang,Shi Zhong-zhi,et al.Researchand Advances on Deep Learning[J].Computer Science,2016,3(2):1-8(in Chinese) 孙志远,鲁成祥,史忠植,等.深度学习研究与进展[J].计算机科学,2016,3(2):1-8
[13] Cover T M,Thomas J A.Elements of Information Theory(2nd Edition)[M].New Jersey:Wiley Inter Science Publication,John Wiely & Sons,Inc.,2006
[14] Hinton G,Salakhutdinov R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,3(5786):504-507
[15] Yu Kai,Jia Lei,Chen Yu-qiang,et al.Deep Learning:Yesterday,Today,and Tomorrow[J].Journal of Computer Research and Development,2013,0(9):1799-1804(in Chinese) 余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,0(9):1799-1804
[16] Guo Li-li,Ding Shi-fei.Research Progress on Deep Learning[J].Computer Science,2015,42(5):28-33(in Chinese) 郭丽丽,丁世飞.深度学习研究进展[J].计算机科学,2015,42(5):28-33
[17] Lee H,Grosse R,Ranganath R,et al.Convolutional deep beliefnetworks for scalable unsupervised learning of hierarchical representations[C]∥Proceedings of the 26th Annual InternationalConferenceon Machine Learning.New York,USA:ACM,2009:609-616
[18] Hinton G,Osindero S I Y.A fast learning algorithm for deepbelief nets[J].Neural Computation,2006,8(7):1527-1554
[19] Hinton G,Sejnowski T.Learning and relearng in Boltzmann machines[C]∥Parallel Distributed Processing:Explorations in the Microstructure of Cognition.Cambridge,USA,1986:45-76
[20] Zhang Chun-xia,Ji Nan-nan,Wang Guan-wei.Restricted Boltzmann Machines[J].Chinese Journal of Engineering Mathema-tics,2015,2(2):159-173(in Chinese) 张春霞,姬楠楠,王冠伟.受限波尔兹曼机[J].工程数学学报,2015,2(2):159-173
[21] Smolensky P.Information processing in dynamical systems:foun-dations of harmony theory[M]∥Parallel Distributed Proces-sing:Explorations in the Microstructure of Cognition.Cambridge,USA,1986:194-281
[22] Freund Y,Haussler D.Unsupervised learning of distributions on binary vectors using two layer networks[R].Santa Cruz:University of California,UCSC-CRL-94-25,4
[23] Roux N,Bengio Y.Representational Power of Restricted Boltzmann Machines and Deep Belief Networks[J].Neural Computation,2008,0(6):1631-1649
[24] Andrieu C,de Freitas N,Doucet A,et al.An introducetion toMCMC for machine learning[J].Machine Learning,2003,0(1/2):5-43
[25] Tieleman T,Hinton G.Using fast weights to improve persistent contrastive divergence[C]∥Proceedings of the 26th InternationalConference on Machine Learning.Helsinki,Finland,2008:1064-1071
[26] Hinton G,Zemel R.Autoencoders,minimum description length,and Helmholtz free energy[C]∥Advances in Neural Information.Processing Systems.Burlington,USA,Morgan Kaufmann,1994:3-10
[27] Vincent P,Bengio Y,Larochelle H,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J].Machine Learning Res,2010,11(12):3371-3408
[28] Rifai S,Vincent P,Muller X,et al.Contractive Auto- Encoders:Explicit Invariance during Feature Extraction[C]∥Proceedings of the 28th International Conference on Machine Learning.New York:ACM,2011:833-840
[29] Olshausen B,Field D.Emergence of simplecell receptive field properties by learning a sparse code for natural images[J].Nature,1996,381(6583):607-609
[30] Olshausen B,Field D.Sparse coding with an overcomplete basis set:a strategy employed by V1? [J].Vision Research,1997,7(23):3311-3326
[31] Lee H,Battle A,Ng A Y,et al.Efficient sparse coding algo-rithms[C]∥Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems,Van-couver.British Columbia,Canada,2006,9:801-808
[32] Lee H,Ekanadham C,Ng A.Sparse deep belief net model for visual area V2[C]∥Proceedings of Advanvances In Neural Information Processing Systems.Cambridge,MA:MIT Press,2008:873-880
[33] Han Jun-wei,Zhang Ding-wen,Cheng Gong,et al.Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning Geoscience and Remote Sensing[J].IEEE Journals & Magazines,2015,3(6):3325-3337
[34] Rumelhart D,Hinton G,Williams R.Learning represention by back-propagating errors[J].Nature,1986,3(6088):533-536
[35] Deng L,Yu D.Deep Learning:Methods and Applications[R].NOW Publishers,2014
[36] Hinton G E,Dayan P,Frey B J,et al.The Wake-Sleep Algo-rithm for Self-Organizing Neural Networks[J].Science,1995,268:1158-1161
[37] Salakhutdinov R,Hinton G.Deep Boltzmann Machines[C]∥Proceedings of the 12th International Conference on Artificial Intelligence and Statistics(AISTATS).2009:448-455
[38] Srivastava N,Salakhutdinov R.Multimodal Learning with Deep Boltzmann Machines[J].Journal of Machine Learning Research,2014,15(8):1967-2006
[39] Chen Yu-shi,Lin Zhou-han,Zhao Xing,et al.Deep LearningBased Classification of Hyperspectral Data[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(6):2094-2107
[40] Zhang Yong-feng,Shang Chang-jing.Combining Newton interpolation and deep learning for image classification[J].IET Journals & Magazines,2015,1(1):40-42
[41] Vincent P,Larochelle H,Bengio Y,et al.Extracting and Composing Robust Features with Denoising Autoencoders[C]∥Proceedings of the 25th International Conference on Machine Lear-ning.NewYork:ACM,2008:1096-1103
[42] Markoff J.How many computers to identify a cat?[N].TheNew York Times,2012
[43] Le Q V,Ramzato M,Ng A,et al.Building high-level featuresusing large scale unsupervised learning,1112.6209[R].NewYork,USA:Cornell University,2012
[44] Coates A,et al.Deep Learning with COTS HPC Systems[J].JMLR W C P,2013,8(3):1337-1345
[45] Rosenblatt F.The perceptron-a perceiving and recognizing automaton[C]∥Math.Stat..1957
[46] Hinton G.Learning distributed representations of concept[C]∥Proceedings of the Eighth Annual Conference of Thecognitive Science Society.1986
[47] Hubel D H,Wiesel T N.Receptive Fields,Binocular Interaction.and Functional Architecture in the Cat’s VisualCortex[J].The Journal of Physiology,1962,160(1):106-154
[48] LeCun Y,Kavukcuoglu K,Farabet C.Convolutional Networksand Applications in Vision[C]∥Proceedings of 2010 IEEE International Symposium on Circuits and Systems(ISCAS).IEEE,2010:253-256
[49] LeCun Y,Bengio Y,Hinton G.Deep Learing[J].Nature Magazines,2015,1(7553):436-444
[50] Hinton G,Li Deng,Dong Yu,et al.Deep neural networks for acoustic modeling in speech recognition:The shared views of four researchgroups[J].IEEE Signal.Process.Mag,2012,9(6):82-97
[51] Ranzato M A,Hinton G E.Modeling pixel means and covaria-nces using factorized third-order boltzmann machines[C]∥IEEE Conference on Computer Vision and Pattern Recognition.SanFrancisco.CA:IEEE,2010:2551-2558
[52] Larochelle H,Murray I.The neural autoregressive distributeon estimator[C]∥Proceedings of the 14th International Conference on Artificial Intelligence and Statistics.Fort Lauderdale,FL,United states:Microtome Publishing,2011:29-37
[53] Chang Hang,Zhou Yin,Borowsky A,et al.Stacked Predictive Sparse Decomposition for Classification of Histology Sections[J].International Journal of Computer Vision (IJCV),2015,3(1):3-18
[54] Krizhevsky A,Sutskever I,Hinton G E.ImageNet Classification with Deep Convolutional Neural Networks Neural Information Processing Systems 25.Neural Information[J].Advances in Neural Information Processing Systems,2012,25(2):2012
[55] Go Master Walloped by Emotionless Challenger,a Google Computer Program[N].The New York Times.
[56] Robot Vision Group.National Laboratory of Pattern Recogn-tion,Institute of Automation,Chinese Academy of Sciences [EB/OL].
[57] Chen T,Du Z,Sun N,et al.DianNao:a small-footprint high-throughput accelerator for ubiquitous machine-learning[J].ACM Sigplan Notices,2014,9(4):269-284
[58] Liu Shao-li,Chen Yun-ji,Chen Tian-shi,et al.DianNaoYu:An Instruction Set Architecture for Neural Networks[C]∥Procee-dings of the 43rd ACM/IEEE International Symposium on Computer Architecture(ISCA’16).2016:393-405
[59] Hu Zhen,Fu Kun,Zhang Chang-shui.Audio Classical Composer Identification by Deep Neural NetWork[J].Journal of Computer Research and Development,2014,1(9):1945-1954(in Chinese) 胡振,傅昆,张长水.基于深度学习的作曲家分类问题[J].计算机研究与发展,2014,1(9):1945-1954
[60] Li Jian-cheng,Yan Chun,Song You.Multilabel Image Annota-tion Based on Convolutional Neural Network[J].Computer Science,2016,43(7):41-45(in Chinese) 黎健成,袁春,宋友.基于卷积神经网络的多标签图像自动标注[J].计算机科学,2016,3(7):41-45
[61] Peng Bo,Zang Di.Vehicle Logo Recognition Based on DeepLearning[J].Computer Science,2015,2(4):268-273(in Chinese) 彭博,臧笛.基于深度学习的车标识别方法研究[J].计算机科学,2015,2(4):268-273
[62] Shi Jing-lan,Chang Kan,Zhang Zhi-yong,et al.Coefficient-similarity-based Dictionary Learning Algorithm for Face Recognition[J].Computer Science,2016,3(6):298-302(in Chinese) 施静兰,常侃,张智勇,等.人脸识别中基于系数相似性的字典学习算法[J].计算机科学,2016,3(6):298-302
[63] He K,Zhang X,Ren S,et al.Delving Deep into Rectifiers:Surpassing Human-Level Performance on ImageNetClassification[J].arXiv:1502.01852
[64] He K,Zhang X,Ren S,et al.Deep Residual Learning for Image Recognition[J].arXiv:1512.03385
[65] Socher R,Huval B,Ng A Y,et al.Convolutional-Recursive Deep Learning for 3D Object Classification[C]∥Neural Information Processing Systems Conference(NIPS).2012:665-673
[66] Sun Ning,Han Guang,Du Kun,et al.Person/vehicle classification based on deep belief networks[C]∥2014 10th International Conference on Natural Computation(ICNC).2014:113-117
[67] Bo Yu,Lane I.Multitask deep learning for image understanding multi-task training[C]∥ 2014 6th International Conference of Soft Computing and Pattern Recognition(SoCPaR).2015:37-42
[68] Sun Y,Wang X,Tang X.Deep learning face representation from predicting 10000 classes[C]∥2014 IEEE Conference on CVPR.2014:1891-189
[69] Sun Y,Chen Y,Wang X,et al.Deep learning face representa-tion by joint identification-verification[C]∥Advances in N- eural Information Processing Systems.2014:1988-1996
[70] Sun Y,Wang X,Tang X.Deeply learned face representations are sparse,selective,and robust[C]∥2015 IEEE Conference on CVPR.2015:2892-2900
[71] Sawada Y,Kozuka K.Transfer learning method using multip-rediction deep Boltzmann machines for a small scaledataset[C]∥2015 14th IAPR International Conference MachineVision Applications (MVA).2015:110-113
[72] Tang Jie-xiong,Deng Chen-wei,Huang Guang-bin,et al.Compressed-Domain Ship Detection on Spaceborne Optical Image Using Deep Neural Network and Extreme Learning Machine[J].IEEE Transactions on Geoscience and Remote Sensing,2015,3(3):1174-1185
[73] Chen Xue-yun,Xiang Shi-ming,Liu Cheng-lin,et al.Aircraft Detection by Deep Belief Nets[C]∥2013 2nd IAPRA-sian Conference on ACPR.2013:54-58
[74] Chen Xue-yun,Xiang Shi-ming,Liu Cheng-lin,et al.Vehicle Detection in Satellite Images by Parallel Deep Convolutional Neural Networks[C]∥2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR).2013:181-185
[75] Wu G,Kim M,Wang Q,et al.Scalable High Performance Image Registration Framework by Unsupervised Deep Feature RepresentationsLearning[J].IEEE Transactions on Biomedical Engineering,2016,63(7):1
[76] Xu Yan,Mo Tao,Feng Qi-wei,et al.Deep learning of feature representation with multiple instance learning for medical image analysis[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2014:1626-1630
[77] Ouyang Wan-li,Wang Xiao-gang,Zeng Xing-yu.Deep-ID-Net:Deformable deep convolutional neural networks for object detection[C]∥IEEE Conference on CVPR,2015:2403-2412
[78] Girshick R,Donahue J,Darrell T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥IEEE Conference on CVPR,2014:580-587
[79] Girshick R.Fast-R-CNN[J].arXiv:1504.08083v2
[80] Larsson G,Maire M,Shakhnarvich G.FractalNet:Ultra-Deep Neural Networks without Residuals[J].arXiv:1605.07648vl
[81] Gary Stix.

No related articles found!
Full text



[1] LEI Li-hui and WANG Jing. Parallelization of LTL Model Checking Based on Possibility Measure[J]. Computer Science, 2018, 45(4): 71 -75, 88 .
[2] XIA Qing-xun and ZHUANG Yi. Remote Attestation Mechanism Based on Locality Principle[J]. Computer Science, 2018, 45(4): 148 -151, 162 .
[3] LI Bai-shen, LI Ling-zhi, SUN Yong and ZHU Yan-qin. Intranet Defense Algorithm Based on Pseudo Boosting Decision Tree[J]. Computer Science, 2018, 45(4): 157 -162 .
[4] WANG Huan, ZHANG Yun-feng and ZHANG Yan. Rapid Decision Method for Repairing Sequence Based on CFDs[J]. Computer Science, 2018, 45(3): 311 -316 .
[5] SUN Qi, JIN Yan, HE Kun and XU Ling-xuan. Hybrid Evolutionary Algorithm for Solving Mixed Capacitated General Routing Problem[J]. Computer Science, 2018, 45(4): 76 -82 .
[6] ZHANG Jia-nan and XIAO Ming-yu. Approximation Algorithm for Weighted Mixed Domination Problem[J]. Computer Science, 2018, 45(4): 83 -88 .
[7] WU Jian-hui, HUANG Zhong-xiang, LI Wu, WU Jian-hui, PENG Xin and ZHANG Sheng. Robustness Optimization of Sequence Decision in Urban Road Construction[J]. Computer Science, 2018, 45(4): 89 -93 .
[8] LIU Qin. Study on Data Quality Based on Constraint in Computer Forensics[J]. Computer Science, 2018, 45(4): 169 -172 .
[9] ZHONG Fei and YANG Bin. License Plate Detection Based on Principal Component Analysis Network[J]. Computer Science, 2018, 45(3): 268 -273 .
[10] SHI Wen-jun, WU Ji-gang and LUO Yu-chun. Fast and Efficient Scheduling Algorithms for Mobile Cloud Offloading[J]. Computer Science, 2018, 45(4): 94 -99, 116 .