Modeling Natural Images Using Gated MRFs

By Marc'Aurelio Ranzato, Volodymyr Mnih, J. Susskind, Geoffrey E. Hinton. 2013

61 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

In Probabilistic & Bayesian Methods

Citations in the corpus

Context Encoders: Feature Learning by Inpainting (2016, neutral): “Recently, Radford et al .”
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (2015, methodology): “Restricted Boltzmann machines [14, 18, 21, 23], Deep Boltzmann machines [26, 8], Denoising auto-encoders [30] all have a generative decoder that reconstructs the image from the latent representation.”
Video (language) modeling: a baseline for generative models of natural videos (2014, background): “tion of natural images which is highly concentrated and multimodal. Although some recent works have shown some progress on smaller resolution images (Goodfellow et al., 2014; Zoran & Weiss, 2012; Ranzato et al., 2013; Theis et al., 2011) using generative models, it is unclear how these models ca”
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks (2013, methodology): “Although we did use neither pretraining nor unlabeled samples, our result is close to the current state-of-the-art rate on the permutation-invariant version of the task reported by (Ranzato et al., 2013) who pretrained their models with a large amount of unlabeled samples.”
Real or Fake? Learning to Discriminate Machine from Human Generated Text (2019, neutral): “While there are works exploring the use of EBMs for modeling images (Teh et al., 2003; Ranzato et al., 2013; Du & Mordatch, 2019), they have not been successfully applied to text.”
Deep Facial Expression Recognition: A Survey (2018, methodology): “In light of this work, [178], [191], [192] employed DBN with unsupervised learning to construct facial expression synthesis systems.”
Energy-Based Models for Text (2020, background): “, 2006), especially in the image domain (Teh et al., 2003; Ranzato et al., 2013).”
High-order neural networks and kernel methods for peptide-MHC binding prediction (2015, methodology): “During pre-training, we used Contrastive Divergence (Hinton, 2002) to learn the factorized weights in mcRBM as in Gaussian RBM, and we used Hybrid Monte Carlo sampling to generate the negative samples as in Ranzato et al. (2013) with 20 leap-frog steps.”
A Survey on Deep Learning (2018, background): “However, with the rapid increases in the size and complexity of data, unsupervised learning will be the dominant solution in the future [111].”
Randomized Max-Margin Compositions for Visual Recognition (2014, background): “Moreover, the individual contributions of compositions and their parts are evaluated in separate experiments that demonstrate their potential.”
Residual Energy-Based Models for Text (2021, background): “Energy-based models (EBMs) have a long history in machine learning (Hopﬁeld, 1982; Hinton, 2002a; LeCun et al., 2006), especially in the image domain (Teh et al., 2003; Ranzato et al., 2013).”
Applications of artificial intelligence for disaster management (2020, unknown): “In this regard, applying and improving unsupervised learning approaches may be the way out for handling real-world data without manual human labels (Ranzato et al. 2013).”