Capsule Networks – A survey

Abdel-hamid, 2014, Convolutional Neural Networks for Speech Recognition. IEEE/ACM Trans. AUDIO, SPEECH, Lang. Process., 22, 1533 Afshary, 2018, Brain tumor type classification via capsule networks, arXiv: 1802.10200v2 [cs.CV] Amer, 2019, Path capsule networks, arXiv: 1902.03760v1 [cs.LG] Annabi, 2018, State representation learning with recurrent capsule networks, arXiv: 1812.11202v4 [cs.LG] Bahadori, 2018, Spectral Capsule Networks, 1 Berman, 2019, DGA CapsNet: 1D Application of Capsule Networks to DGA Detection, Information, 10, 1, 10.3390/info10050157 Bordes, 2013, Translating embeddings for modeling multi-relational data, Adv. Neural Inf. Process. Syst., 1–9 Busso, 2008, 1 Chao, 2019, Emotion Recognition from Multiband EEG Signals Using CapsNet, Sensors, 19, 1, 10.3390/s19092212 Chauhan, A., Babu, M., Kandru, N., Lokegaonkar, S., 2018. Empirical Study on convergence of Capsule Networks with various hyperparameters. http://people.cs.vt.edu/~bhuang/courses/opt18/projects/capsule.pdf. Chen, 2017, Fast Image Processing with Fully-Convolutional Networks, 2497 Chen, 2018, Generalized Capsule Networks with Trainable Routing Procedure, arXiv1808.08692v1 [cs.CV], 1 Cheng, 2015, Enhanced performance of brain tumor classification via tumor region augmentation and partition, PLoS One, 10, 1 Cheng, 2016, Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation, PLoS One, 11, 1 Clercq, 2018, IEST: WASSA-2018 Implicit Emotions Shared Task, arXiv:1809.01083v2 [cs.CL], 1 Deliege, 2018, HitNet : a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules, arXiv:1806.06519v1 [cs.CV], 1 Deng, 2018, Attention-based capsule networks with dynamic routing for relation extraction, extracarXiv: 1812.11321v1 [cs.IR] Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S., 2017. Convolutional 2D knowledge graph embeddings. https://arxiv.org/abs/1707.01476. Dey, 2016, Image processing based leaf rot disease, detection of betel vine, Procedia Comput. Sci., 85, 748, 10.1016/j.procs.2016.05.262 DiPietro, R., 2016. A Friendly Introduction to Cross-Entropy Loss [WWW Document]. https://doi.org/10.1109/MDSO.2007.4370101. Dombetzki, 2018, An overview over Capsule Networks, 89 Duarte, 2018, VideoCapsuleNet: A Simplified Network for Action Detection, arXiv:1805.08162v1 [cs.CV] Engelbrecht, 2007 Engelin, 2018 Fang, 2018, Improving protein gamma-turn inception capsule networks prediction using inception capsule networks, Nature Fasel, 2003, Automatic facial expression analysis: a survey, Pattern Recognit., 36, 259, 10.1016/S0031-3203(02)00052-3 Gao, 2018, On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning, arXiv:1704.00805v4 [math.OC], 1 Garg, 2017, Using Capsule Networks with Thermometer Encoding to Defend Against Adversarial Attacks Glorot, 2011, Deep Sparse Recti er Neural Networks, 315 Golhani, 2018, A review of neural networks in plant disease detection using hyperspectral data, Inf. Process. Agric., 5, 354 Gordienko, 2018, Capsule Deep Neural Network for Recognition of Historical Graffiti Handwriting, IEEE, 3 Gritsevskiy, 2018, Capsule networks for low-data transfer learning, arXiv1804.10172v1 [cs.CV], 1 Guo, 2018, EEG Emotion Recognition Based on Granger Causality and CapsNet Neural Network, 47 He, 2015, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, 1026 He, 2015, Deep Residual Learning for Image Recognition, Microsoft Res. arXiv1512.03385v1 [cs.CV] Hinton, 2018, Matrix capsules with em routing, 1 Hinton, 2011, Transforming auto-encoders, 44 Huang, 2017, Densely connected convolutional networks, 2261 Iesmantas, T., Alzbutas, R., 2018. Convolutional capsule network for classification of breast cancer histology images. https://arxiv.org/abs/1804.08376, 1–8. Iqbal, 2018, Capsule routing for sound event detection, arXiv:1806.04699v1 [cs.SD] Jain, 2019, Improving performance and inference on audio classification tasks using capsule networks, caparXiv: 1902.05069v1 [cs.SD] Jaiswal, 2018, CapsuleGAN: Generative Adversarial Capsule Network, arXiv:1802.06167v7 [stat.ML], 1 Jesus, 2018, Capsule Networks for Protein Structure Classification and Prediction, arXiv:1808.07475v1 [cs.LG] Jimenez-Sanchez, 2018, Capsule Networks against Medical Imaging Data Challenges, arXiv:1807.07559v1 [cs.CV] Katebi, 2018, Galaxy morphology prediction using capsule networks, arXiv:1809.08377v1 [astro-ph.IM] 7, 1 Kauppi, T., Kalesnykiene, V., Kamarainen, J.-K., Lensu, L., Sorri, I., Voutilainen, R., Uusitalo, H., K¨alvi¨ainen, H., Pietil¨, J., 2007. DIARETDB1-standard diabetic retino-pathy database [WWW Document]. http://www.it.lut.fi/project/imageret/diaretdb1/doc/diaretdb1_techreport_v_1_1.pdf. URL http://www.bmva.org/bmvc/2007/papers/paper-60.html. Kim, 2018, Text Classification using Capsules, arXiv:1808.03976v2 [cs.CL], 1 Kim, 2018, Detection of centerline crossing in abnormal driving using CapsNet, J. Supercomput. Kim, 2018, A Capsule Network for Traffic Speed Prediction in Complex Road Networks, arXiv:1807.10603v2 [cs.CV] Koelstra, 2011, DEAP: A Database for Emotion Analysis using Physiological Signals, IEEE TRANS. Affect. Comput., 1 Krizhevsky, A., Hinton, G., 2009. Learning Multiple Layers of Features from Tiny Images [WWW Document]. URL http://www.cs.toronto.edu/~kriz/cifar.html. (Accessed 6.15.19). Kumar, A.D., Karthika, R., Parameswaran, L., 2018. Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks. https://arxiv.org/abs/1805.04424. Kung, H.T., 1982. Why Systolic Architectures [WWW Document]. URL www.eecs.harvard.edu/~htk/.../1982-kung-why-systolic-architecture.pdf. (Accessed 6.6.19). Kuo, 2016, Understanding convolutional neural networks with a mathematical model, J. Vis. Commun. Image Represent., 41, 406, 10.1016/j.jvcir.2016.11.003 Lalonde, 2018, Capsules for Object Segmentation, arXiv1804.04241v1 [stat.ML], 1 Larsson, 2017, FractalNet: Ultra-Deep Neural Networks without Residuals, arXiv1605.07648v4 [cs.CV], 1 Lecun, 2015, Deep learning, Nature, 52 LeCun, 2014, Backpropagation applied to handwritten zip code recognition, Sci. Signal., 7, 541 LeCun, 1998, Gradient-based learning applied to document recognition, 1 LeCun, Y., Bottou, L., Orr, G.B., Muller, K.-R., 1998b. Efficient BackProp [WWW Document]. Neural Networks: tricks of the trade, Springer. URL http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf. (Accessed 6.17.19). LeCun, Y., Cortes, C., Burges, C.J.C., 1998c. MNIST [WWW Document]. URL http://yann.lecun.com/exdb/mnist/. (Accessed 6.15.19). LeCun, 2004, Learning methods for generic object recognition with invariance to pose and lighting Lenssen, 2018, Group Equivariant Capsule Networks, arXiv:1806.05086v2 [cs.CV] Li, 2018, Cognitive Consistency Routing Algorithm of, arXiv:1808.09062v3 [cs.AI] Li, 2018, Fully CapsNet for Semantic Segmentation, 392 Lin, 2018, On Learning and Learned Representation with Dynamic Routing in Capsule Networks, arXiv:1810.04041v1 [cs.CV] Liu, 2014, A strategy on selecting performance metrics for classifier evaluation, Int. J. Mob. Comput. Multimed. Commun., 6, 20, 10.4018/IJMCMC.2014100102 Ma, 2019, TCDCaps: Visual Tracking via Cascaded Dense Capsules, arXiv:1902.10054v1 [cs.CV] Ma, 2017, Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction, Sensors (Switzerland), 17, 1, 10.3390/s17040818 Ma, X., Li, Y., Cui, Z., Wang, Y., 2018. Forecasting Transportation Network Speed Using Deep Capsule Networks with Nested LSTM Models. https://arxiv.org/pdf/1811.04745. Mallea, 2019, Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations, arXiv:1902.08399v1 [cs.LG] Mandal, 2019, Handwritten Indic Character Recognition using Capsule Networks, arXiv:1901.00166v1 [cs.CV] Marchisio, 2018, X-TrainCaps: Accelerated Training of Capsule Nets through Lightweight Software Optimizations, ArXiv Prepr. arXiv1905.10142, 1 Marchisio, 2018, CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse, arXiv:1811.08932v1 [cs.DC] Marchisio, 2019, CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks, arXiv:1901.09878v1 [cs.LG] McCormick, 2015, KRAS as a therapeutic target, Clin. Cancer Res., 21, 1797, 10.1158/1078-0432.CCR-14-2662 Mhaskar, H.N., Micchelli, C.A., 1994. How to Choose an Activation Function [WWW Document]. URL https://papers.nips.cc/paper/874-how-to-choose-an-activation-function.pdf. (Accessed 7.6.19). Mikolov, 2013, Efficient Estimation of Word Representations in Vector Space, arXiv:1301.3781v3 [cs.CL], 1 Mobiny, 2018, Fast CapsNet for Lung Cancer Screening, arXiv:1806.07416v1 [cs.CV] Mukhometzianov, R., Carrillo, J., 2018. CapsNet comparative performance evaluation for image classification. https://arxiv.org/abs/1805.11195 1–14. Nair, P., Doshi, R., Keselj, S., 2018. Pushing the Limits of Capsule Networks, https://arxiv.org/abs/1804.04241, 1–16. Neill, 2018, Siamese Capsule Networks, arXiv:1805.07242v1 [stat.ML], 1 Netzer, 2011, Reading digits in natural images with unsupervised feature learning, 1 Nguyen, Dai Quoc, Nguyen, T.D., Nguyen, Dat Quoc, Phung, D., 2017. A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network. https://arxiv.org/abs/1712.02121, https://doi.org/10.18653/v1/N18-2053. Nguyen, 2019, A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization, arXiv:1808.04122v3 [cs.CL] Nguyen, 2018, Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos, arXiv:1810.11215v1 [cs.CV] Nguyen, 2015, Relation Extraction: Perspective from Convolutional Neural Networks Thien, 27 Nielson, M., 2019. Neural Networks and Deep Learning [WWW Document]. URL http://neuralnetworksanddeeplearning.com/chap2.html. (Accessed 6.17.19). Pal, 2018, CapsDeMM: Capsule network for Detection of Munro’s Microabscess in skin biopsy images, arXiv:1808.06428v2 [cs.CV] Pattanayak, 2017 Paul, J., 2016. Deep learning for brain tumor classification (Masters Thesis). https://doi.org/10.1117/12.2254195. Peer, 2018, Training Deep Capsule Networks, arXiv:1812.09707v1 [cs.LG] Phaye, 2018, Dense and Diverse Capsule Networks: Making the Capsules Learn Better, arXiv 1805.04001v1 [cs.CV], 1 Phong, 2019, Advanced Capsule Networks via Context Awareness, arXiv1903.07497v2 [cs.LG], 1 Popperl, 2019, Capsule Neural Network based Height Classification using Low-Cost Automotive Ultrasonic Sensors, arXiv1902.09839v1 [cs.CV] Prakash, 2018, Simultaneous Localization And Mapping with depth Prediction using Capsule Networks for UAVs, arXiv:1808.05336v1 [cs.RO] Radford, 2015, Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 1 Ragoza, 2017, Protein-Ligand Scoring with Convolutional Neural Networks, J. Chem. Inf. Model., 57, 942, 10.1021/acs.jcim.6b00740 Raj, 2017, Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text, 311 Rajasegaran, 2019, DeepCaps: Going Deeper with Capsule Networks, ArXiv Prepr. arXiv1904.09546, 1 Ramasinghe, 2018, A Context-aware Capsule Network for Multi-label Classi cation, arXiv 1810.06231v2 [cs.CV], 1 Rathnayaka, 2018, Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection, represenarXiv: 1809.01452v1 [cs.CL] Rawlinson, 2018, Sparse Unsupervised Capsules Generalize Better, arXiv:1804.06094v1 [cs.CV] Ren, 2018, Compositional Coding Capsule Network with K-Means Routing for Text Classification, arXiv:1810.09177v3 [cs.LG] Ren, 2019, Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification, arXiv:1901.10112v2 [cs.CV] Renkens, 2018, Capsule Networks for Low Resource Spoken Language Understanding, arXiv:1805.02922v1 [eess.AS] Riedel, 2014, Modeling Relations and Their Mentions without Labeled Text, 148 Rosario, 2019, The Multi-Lane Capsule Network (MLCN), arXiv:1902.08431v1 [cs.CV], 1 Russakovsky, 2015, ImageNet large scale visual recognition challenge, Int. J. Comput. Vis., 10.1007/s11263-015-0816-y Sabour, 2017, Dynamic Routing Between Capsules Saha, S., 2018. A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way [WWW Document]. https://doi.org/10.1080/09640560500294277. Salamon, 2016, Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification, IEEE Signal Process. Lett., 1 dos Santos, 2015, Classifying Relations by Ranking with Convolutional Neural Networks, arXiv:1504.06580v2 [cs.CL] Saqur, 2018, CapsGAN: Using Dynamic Routing for Generative Adversarial Networks, arXiv:1806.03968v1 [cs.CV] Sastry, S., 2018. Recurrent Capsule Network for Image Generation. vixra.org/pdf/1804.0112v1.pdf, pp. 1–9. Scherer, 2010, Evaluation of pooling operations in convolutional architectures for object recognition, 92 SETA Project [WWW Document], 2016. A ubiquitous data Serv. Ecosyst. better Metrop. Mobil. URL http://setamobility.weebly.com/. (Accessed 6.17.19). Shahroudnejad, 2018, Improved Explainability of Capsule Networks: Relevance Path by Agreement, arXiv:1802.10204v1 [cs.CV] Simonyan, 2015, Very deep convolutional networks for large-scale image recognition, 1 Sladojevic, 2016, Deep neural networks based recognition of plant diseases by leaf image classification, Comput. Intell. Neurosci., 2016, 10.1155/2016/3289801 Sorokin, 2017, Context-Aware Representations for Knowledge Base Relation Extraction, 1784 Su, 2019, One pixel attack for fooling deep neural networks, IEEE Trans. Evol. Comput., 1–15 Su, 2019, Attacking convolutional neural network using differential evolution, IPSJ Trans. Comput. Vis. Appl., 11, 1, 10.1186/s41074-019-0053-3 Sukittanon, 2004, Convolutional networks for speech detection Sun, 2017, A facial expression recognition method based on ensemble of 3D convolutional neural networks, Neural Comput. Appl., 1–18 Tobing, 2018, EP-CapsNet : Extending Capsule Network with Inception Module for Electrophoresis Binary Classification, 327 Toutanova, 2015, Observed versus latent features for knowledge base and text inference, 57 Upadhyay, 2018, Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks, arXiv:1806.03796v4 [cs.CV] Verma, 2018, Graph Capsule Convolutional Neural Networks Vesperini, 2018, Polyphonic Sound Event Detection by using Capsule Neural Networks, J. Sel. Top. SIGNAL Process. X, 1 Vu, T., Nguyen, D.Q., Johnson, M., Song, D., Willis, A., 2017. Search personalization with embeddings. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) https//arxiv.org/abs/1612.03597, 10193 LNCS, 598–604. https://doi.org/10.1007/978-3-319-56608-5_54. Wang, 2018, An optimization view on dynamic routing between capsules, 1 Wang, 2018, Towards Linear Time Neural Machine Translation with Capsule Networks, arXiv:1811.00287v1 [cs.CL] Wang, 2018, Automatic Severity Classification of Coronary Artery Disease via Recurrent Capsule Network, arXiv:1807.06718v2 [cs.CL] Wang, 2018, Sentiment Analysis by Capsules, 1165 Wong, 2016, Understanding Data Augmentation for Classification: When to Warp? Wu, 2017, Introduction to convolutional neural networks, Natl. Key Lab Nov. Softw. Technol., 1–31 Xi, 2017, Capsule Network Performance on Complex Data, arXiv1712.03480v1 [stat.ML], 1 Xia, 2018, Zero-shot User Intent Detection via Capsule Neural Networks, metharXiv 1809.00385v1 [cs.CL] Xiang, 2018, MS-CapsNet: A Novel Multi-Scale Capsule Network, IEEE Signal Process. Lett., 1 Xiao, 2017, Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms, arXiv:1708.07747v2 [cs.LG], 1 Yang, 2019, Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical solution, caparXiv 1903.10588v2 [cs.LG] Zhang, 2018, Joint Slot Filling and Intent Detection via Capsule Neural Networks, arXiv:1812.09471v1 [cs.CL] Zhang, 2015, Relation Classification via Recurrent Neural Network, modarXiv 1508.01006v2 [cs.CL] Zhang, 2019, 1D-Convolutional Capsule Network for Hyperspectral Image Classification, arXiv:1903.09834v1 [cs.CV], 1 Zhang, 2018, CapProNet : Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces, arXiv:1805.07621v2 [cs.CV] Zhang, 2019, Remote Sensing Image Scene Classification Using CNN-CapsNet, Remote Sens., 11, 1 Zhang, 2019, Fluorescence microscopy image classification of 2D HeLa cells based on the CapsNet neural network, Med. Biol. Eng. Comput., 10.1007/s11517-018-01946-z Zhang, 2018, Multi-labeled Relation Extraction with Attentive Capsule Network, arXiv:1811.04354v1 [cs.CL] Zhang, 2018, Cervical image classification based on image segmentation preprocessing and a CapsNet network model, Int. J. Imaging Syst. Technol., 1–10 Zhao, 2018, Investigating Capsule Networks with Dynamic Routing for Text Classification, arXiv1804.00538v4 [cs.CL] Zhao, 2018, 3D Point-Capsule Networks, arXiv:1812.10775v1 [cs.CV] Zhao, 2019, Capsule Networks with Max-Min Normalization, arXiv:1903.09662v1 [cs.CV], 1 Zhou, 2017, Scene parsing through ADE20K dataset [WWW Document]. Scene Parsing through ADE20K Dataset-, Proc. IEEE Conf. Comput. Vis. Pattern Recognition Zhou, 2016, Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification, 207 Zhou, Y., Liu, Y., 2018. Correlation analysis of performance metrics for classifier. Decis. Mak. Soft Comput. www.worldscientific.com 487–492.