Combining deep generative and discriminative models for Bayesian semi-supervised learning

Bishop, 2006 Blundell, 2015, Weight uncertainty in neural networks, 1613 Bottou, 2010, Large-scale machine learning with stochastic gradient descent, 177 Chapelle, 2010 Cremer, 2018, Inference suboptimality in variational autoencoders, 1078 Cuff, 1999, Evaluation and improvement of multiple sequence methods for protein secondary structure prediction, Proteins, 34, 508, 10.1002/(SICI)1097-0134(19990301)34:4<508::AID-PROT10>3.0.CO;2-4 Dai, 2017, Good semi-supervised learning that requires a bad GAN, 6510 S. Depeweg, J.M. Hernández-Lobato, S. Udluft, T. Runkler, Sensitivity analysis for predictive uncertainty in Bayesian neural networks, arXiv:1712.03605 (2017). Ehsan Abbasnejad, 2017, Infinite variational autoencoder for semi-supervised learning, 5888 Gammulle, 2020, Fine-grained action segmentation using the semi-supervised action GAN, Pattern Recognit., 98, 107039, 10.1016/j.patcog.2019.107039 Gelman, 2013 Goodfellow, 2016 Goodfellow, 2014, Generative adversarial nets, 2672 Gu, 2018, Recent advances in convolutional neural networks, Pattern Recognition, 77, 354, 10.1016/j.patcog.2017.10.013 Guillaumin, 2010, Multimodal semi-supervised learning for image classification, 902 Guo, 2017, On calibration of modern neural networks, 1321 He, 2016, Deep residual learning for image recognition, 770 Hernandez-Lobato, 2016, Black-box alpha divergence minimization, 1511 Hernández-Lobato, 2015, Probabilistic backpropagation for scalable learning of Bayesian neural networks, 1861 Ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 448 Kingma, 2014, Adam: a method for stochastic optimization Kingma, 2014, Semi-supervised learning with deep generative models, 3581 Kingma, 2014, Auto-encoding variational Bayes Kuleshov, 2017, Deep hybrid models: Bridging discriminative and generative approaches Kumar, 2017, Semi-supervised learning with GANs: Manifold invariance with improved inference, 5534 Kuznietsov, 2017, Semi-supervised deep learning for monocular depth map prediction, 6647 Lai, 2019, Improving classification with semi-supervised and fine-grained learning, Pattern Recognit., 88, 547, 10.1016/j.patcog.2018.12.002 Lasserre, 2006, Principled hybrids of generative and discriminative models, 1, 87 LeCun, 2010, MNIST handwritten digit database, AT&T Labs, 2 Maaløe, 2016, Auxiliary deep generative models Maddison, 2017, The concrete distribution: A continuous relaxation of discrete random variables Mahapatra, 2017, Semi-supervised learning and graph cuts for consensus based medical image segmentation, Pattern Recognit., 63, 700, 10.1016/j.patcog.2016.09.030 McCallum, 2006, Multi-conditional learning: Generative/discriminative training for clustering and classification, 433 Minka, 2005, Discriminative models, not discriminative training Misra, 2015, Watch and learn: Semi-supervised learning for object detectors from video, 3593 Naeini, 2015, Obtaining well calibrated probabilities using Bayesian binning., 2901 Neal, 2012, 118 Ng, 2002, On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes, 841 Nogueira, 2017, Towards better exploiting convolutional neural networks for remote sensing scene classification, Pattern Recognit., 61, 539, 10.1016/j.patcog.2016.07.001 Rasmussen, 2001, Occam’s razor, 294 Roth, 2018, Bayesian neural networks with weight sharing using Dirichlet Processes, IEEE Trans. Pattern Anal. Mach. Intell., 1 Schölkopf, 2012, On causal and anticausal learning, 1255 Settles, 2012, Active learning, Synthesis Lect. Artif. Intell. Mach. Learn., 6, 1, 10.2200/S00429ED1V01Y201207AIM018 Sheikhpour, 2017, A survey on semi-supervised feature selection methods, Pattern Recognit., 64, 141, 10.1016/j.patcog.2016.11.003 Silver, 2016, Mastering the game of GO with deep neural networks and tree search, Nature, 529, 484, 10.1038/nature16961 Snoek, 2015, Scalable Bayesian optimization using deep neural networks., 2171 Turner, 2011, Two problems with variational expectation maximisation for time-series models, Bayesian Time Ser. Models, 1, 1 H. Xiao, K. Rasul, R. Vollgraf, Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms, 2017, arXiv:cs.LG/1708.07747. Zhang, 2019, Advances in variational inference, IEEE Trans. Pattern Anal. Mach.Intell., 41, 2008, 10.1109/TPAMI.2018.2889774