A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

zhu, 2016, Trained ternary quantization, arXiv 1612 01064

micikevicius, 2017, Mixed precision training, arXiv 1710 03740

choi, 2016, Towards the limit of network quantization, arXiv 1612 01543

itqan, 2016, User identification system based on finger-vein patterns using convolutional neural network, ARPN J Eng Appl Sci, 11, 3316

10.1016/j.patrec.2018.02.015

10.1109/ACCESS.2018.2810882

hamidian, 2017, 3D convolutional neural network for automatic detection of lung nodules in chest CT, Proc SPIE, 10134

10.1109/AVSS.2017.8078501

10.1016/j.proeng.2017.09.594

10.1007/978-3-319-46493-0_32

lin, 2017, Towards accurate binary convolutional neural network, arXiv 1711 11294

simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv 1409 1556

10.1145/3178876.3186116

10.1109/IJCNN.2005.1555942

weiler, 2019, General $E(2)$ -equivariant steerable CNNs, arXiv 1911 08251

weiler, 2018, 3D steerable CNNs: Learning rotationally equivariant features in volumetric data, arXiv 1807 02547

cohen, 2016, Steerable CNNs, arXiv 1612 08498

10.1609/aaai.v32i1.11691

kipf, 2016, Semi-supervised classification with graph convolutional networks, arXiv 1609 02907

bruna, 2013, Spectral networks and locally connected networks on graphs, arXiv 1312 6203

10.1109/TNN.2008.2005605

bhagoji, 2019, Analyzing federated learning through an adversarial lens, Proc Int Conf Mach Learn, 634

liao, 2018, Backdoor embedding in convolutional neural network models via invisible perturbation, arXiv 1808 10307

cai, 2018, ProxylessNAS: Direct neural architecture search on target task and hardware, arXiv 1812 00332

10.1109/ACCESS.2018.2807385

10.1007/978-3-030-00470-5_13

goodfellow, 2014, Explaining and harnessing adversarial examples, arXiv 1412 6572

10.1109/CVPR.2019.00720

10.1109/CVPR.2019.00293

pham, 2018, Efficient neural architecture search via parameters sharing, Proc Int Conf Mach Learn, 4095

zoph, 2016, Neural architecture search with reinforcement learning, arXiv 1611 01578

10.1109/CVPR.2018.00291

10.1109/CVPR.2017.634

10.1007/978-3-030-36808-1_7

10.1109/ICCV.2019.00364

10.1113/jphysiol.1962.sp006837

10.1007/978-3-642-46466-9_18

10.1021/ci0342472

10.1109/ICCV.2017.89

yu, 2016, Multi-scale context aggregation by dilated convolutions, arXiv 1511 07122

dong, 2020, CoDeNet: Efficient deployment of input-adaptive object detection on embedded FPGAs, arXiv 2006 08357

10.1109/CVPR.2019.00953

10.1007/978-3-030-01249-6_18

10.1109/CVPR.2018.00745

cao, 2016, Action recognition with joints-pooled 3D deep convolutional descriptors, Proc IJCAI, 1, 3

10.1109/CVPR.2018.00552

10.1109/TCSVT.2018.2870740

10.1109/ICMLA.2019.00036

10.1109/CVPR.2014.220

10.1109/CVPR.2019.00482

10.1109/CVPR.2017.713

10.1109/ICCV.2019.00925

10.1109/ICCV.2017.324

10.1109/CVPR.2019.00963

10.1109/CVPR.2019.00633

krizhevsky, 2010, Convolutional deep belief networks on CIFAR-10, Unpublished manuscript, 40, 1

10.1109/ICCV.2015.123

hagan, 2002, Neural Network Design, 9

nair, 2010, Rectified linear units improve restricted Boltzmann machines, Proc ICML, 807

10.1109/TNN.2008.2010350

10.1109/CVPR42600.2020.00165

10.1007/978-3-030-01264-9_8

10.1109/CVPR.2018.00716

10.1109/CVPR.2015.7298594

mao, 2017, Exploring the regularity of sparse structure in convolutional neural networks, arXiv 1705 08922

han, 2015, Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding, arXiv 1510 00149 [cs]

sindhwani, 2015, Structured transforms for small-footprint deep learning, arXiv 1510 01722

10.5244/C.28.88

10.1117/12.2293725

10.3390/s19245356

10.1109/CVPR.2018.00472

10.1109/CVPR.2016.94

10.1038/323533a0

10.21236/AD0256582

zhang, 1988, Shift-invariant pattern recognition neural network and its optical architecture, Proc Annu Conf Jpn Soc Appl Phys, 734

10.1109/29.21701

10.1016/0375-9601(90)90136-C

10.1109/IROS.2015.7353481

10.1162/neco.1989.1.4.541

10.1109/CVPR.2017.195

huang, 2018, Human action recognition based on temporal pose CNN and multi-dimensional fusion, Proc Eur Conf Comput Vis (ECCV) Workshops, 1

10.1109/72.97934

wu, 2015, 3D ShapeNets: A deep representation for volumetric shapes, Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), 1912

howard, 2017, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv 1704 04861

radford, 2015, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv 1511 06434

10.1109/ICCV.2019.00140

10.1109/CVPR.2018.00474

10.1109/CVPR.2016.308

ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc Int Conf Mach Learn, 448

10.1109/CVPR.2016.90

10.1609/aaai.v31i1.11231

amos, 2016, OpenFace: A general-purpose face recognition library with mobile applications

10.5244/C.29.41

10.1109/CVPR.2015.7298682

sun, 2015, DeepID3: Face recognition with very deep neural networks, arXiv 1502 00873

10.1109/IJCNN.2019.8852059

10.1007/978-3-319-46478-7_31

10.1109/CVPR.2016.149

hermans, 2017, In defense of the triplet loss for person re-identification, arXiv 1703 07737

10.1007/978-3-319-70096-0_42

10.1109/BTAS.2017.8272706

clevert, 2015, Fast and accurate deep network learning by exponential linear units (ELUs), arXiv 1511 07289

misra, 2019, Mish: A self regularized non-monotonic activation function, arXiv 1908 08681

ramachandran, 2017, Searching for activation functions, arXiv 1710 05941

xiao, 2017, Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms, ArXiv 1708 07747

krizhevsky, 2009, Learning multiple layers of features from tiny images

10.1109/CVPR.2009.5206848

10.1109/CVPR.2006.100

10.1109/CVPR.2005.202

10.1109/CVPR.2014.244

10.1109/CVPR.2015.7298907

ovtcharov, 2015, Accelerating deep convolutional neural networks using specialized hardware, 2, 1

sabour, 2017, Dynamic routing between capsules, arXiv 1710 09829

kosiorek, 2019, Stacked capsule autoencoders, arXiv 1906 06818

azulay, 2018, Why do deep convolutional networks generalize so poorly to small image transformations?, arXiv 1805 12177

10.1109/FPL.2009.5272559

10.1109/CVPRW.2014.106

10.1145/2684746.2689060

10.1109/ICASSP.2016.7472620

chorowski, 2015, Attention-based models for speech recognition, arXiv 1506 07503

jajodia, 2019, Image classification–cat and dog images, Image, 6, 570

zeiler, 2012, ADADELTA: An adaptive learning rate method, arXiv 1212 5701

drews, 2017, Aggressive deep driving: Model predictive control with a CNN cost model, arXiv 1707 05303

duchi, 2011, Adaptive subgradient methods for online learning and stochastic optimization, J Mach Learn Res, 12, 1

10.1109/TII.2018.2822828

10.1109/CVPRW.2015.7301342

10.1016/j.csl.2016.06.007

kingma, 2014, Adam: A method for stochastic optimization, arXiv 1412 6980

sharma, 2015, Action recognition using visual attention, arXiv 1511 04119

rakhlin, 2016, Convolutional neural networks for sentence classification

hinton, 2012, Neural networks for machine learning lecture 6a overview of mini-batch gradient descent

10.1145/3136755.3143008

liu, 2016, Large-margin softmax loss for convolutional neural networks, Proc ICML, 2, 7

saad, 2009, On-Line Learning in Neural Networks

10.21437/Interspeech.2019-2357

10.21437/Interspeech.2017-1067

10.1109/ASCC.2017.8287318

10.1109/CVPR.2017.243

sun, 2014, Deep learning face representation by joint identification-verification, arXiv 1406 4773

10.1016/S0893-6080(98)00116-6

nesterov, 1983, A method for unconstrained convex minimization problem with the rate of convergence O(1/k2), Proc Doklady USSR, 269, 543

zhao, 2016, F-CNN: An FPGA-based framework for training convolutional neural networks, Proc IEEE 27th Int Conf Appl -Specific Syst Archit Processors (ASAP), 107

10.1038/s41598-018-21495-7

10.1109/MLSP.2016.7738895

10.1109/TCAD.2017.2705069

10.1145/2934583.2934644

10.1109/TIP.2018.2809606

10.5220/0007392506130620

10.1109/SBR-LARS-R.2017.8215287

10.1371/journal.pone.0214587

10.1109/CVPR.2016.91

10.1016/j.neunet.2017.07.017

10.1109/CVPR.2017.690

10.1007/978-3-030-01264-9_45

law, 2019, CornerNet-lite: Efficient keypoint based object detection, arXiv 1904 08900

redmon, 2018, YOLOv3: An incremental improvement, arXiv 1804 02767

10.1007/978-3-319-46448-0_2

10.1109/ICCV.2015.169

10.1109/CVPR.2014.81

10.1109/CVPR.2017.106

ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, arXiv 1506 01497

10.1109/CVPR.2015.7298965

ronneberger, 2015, U-Net: Convolutional networks for biomedical image segmentation, Proc Int Conf Med Image Comput Comput -Assist Intervent, 234

paszke, 2016, ENet: A deep neural network architecture for real-time semantic segmentation, ArXiv 1606 02147

10.1109/CVPR.2017.660

10.1109/TPAMI.2017.2699184

10.1037/h0042519

10.1145/3293353.3293406

10.1007/BF02478259

10.1109/ICCV.2017.322

monti, 2019, Fake news detection on social media using geometric deep learning, arXiv 1902 06673

jahanifar, 2018, Segmentation of skin lesions and their attributes using multi-scale convolutional neural networks and domain specific augmentations, arXiv 1809 10243

reddi, 2019, On the convergence of Adam and beyond, arXiv 1904 09237

schindler, 2018, Multi-temporal resolution convolutional neural networks for acoustic scene classification, arXiv 1811 04419

10.1371/journal.pone.0219126

10.18653/v1/W18-2314

dozat, 2016, Incorporating Nesterov momentum into Adam, Proc ICLR, 1

10.1109/ICCV.2017.37

snoek, 2012, Practical Bayesian optimization of machine learning algorithms, arXiv 1206 2944

rapin, 2018, Nevergrad—A Gradient-Free Optimization Platform Version 0 2

liu, 2018, Decompose to manipulate: Manipulable object synthesis in 3D medical images with structured image decomposition, arXiv 1812 01737

10.1109/5.726791

krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, Proc Adv Neural Inf Process Syst, 25, 1097

10.1109/ICCSP.2017.8286426

10.1007/s13748-019-00203-0

10.1162/neco_a_00990

10.1007/978-3-319-63309-1_7

ajmal, 2018, Convolutional neural network based image segmentation: A review, Proc SPIE, 10649

10.1016/j.jsv.2016.10.043

10.4249/scholarpedia.10491

10.1109/ACCESS.2017.2707460

10.1109/CVPR.2005.177

10.1109/TPAMI.2006.244

10.1109/TIE.2018.2886789

10.3346/jkms.2019.34.e64

liu, 2017, ZOOpt: Toolbox for derivative-free optimization, arXiv 1801 00329

10.1177/1550147719832792

10.1016/j.enconman.2019.05.007

10.1109/TPAMI.2015.2389824

chen, 2017, Dual path networks, arXiv 1707 01629

iandola, 2014, DenseNet: Implementing efficient ConvNet descriptor pyramids, Arxiv 1404 1869

10.1109/ICARCV.2014.7064414