On deep generative models with applications to recognition

By Marc'Aurelio Ranzato, J. Susskind, Volodymyr Mnih, Geoffrey E. Hinton. 2011

247 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

A Generative Process for Contractive Auto-Encoders (2012, methodology): “A related idea has also allowed us to train the second layer of a 2-layer CAE, acting like pooling or invariance-seeking features, and this has yielded improvements in classi-5 for comparison, Ranzato et al. (2011) reports that SVM achieve 28.5% and sparse coding : 23.4%.”
Learning to generate chairs with convolutional neural networks (2014, background): “RBMs and DBMs are undirected graphical models which aim to build a probabilistic model of the data and treat encoding and generation as an (intractable) joint inference problem.”
Representation Learning: A Review and New Perspectives (2012, background): “It has been applied in a variety of applications [205], [165], [113], and it has been”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, background): “As a representative example, the restricted Boltzmann machine (RBM) [33] and its variants [28, 25, 30, 15, 37, 31] have been widely studied for image modeling.”
Disentangling Factors of Variation via Generative Entangling (2012, background): “72% 1 , while a deep mPoT model (Ranzato et al., 2011), which exploits local receptive ﬁelds achieves 82 .”
Deep Learning: Methods and Applications (2014, background): “[298], the deep generative model of DBN with gated Markov random field (MRF) at the lowest level is learned for feature extraction and then for recognition of difficult image classes including occlusions.”
Learning Generative Models with Visual Attention (2013, background): “In addition, prior knowledge can be easily incorporated in generative models in the forms of structured latent variables, such as lighting and deformable parts.”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “The generative ability of the DBN model facilitates the discovery of what information is captured and what is lost at each level of representation in the deep model, as demonstrated in [146].”
Artificial Intelligence and Digital Pathology: Challenges and Opportunities (2018, unknown): “Generative models, in contrast, focus on learning to (re) produce data without making any decisions.[47,48] Naïve Bayes, restricted Boltzmann machines, and generative adversarial networks are examples of generative methods.”
Deep Learning Identity-Preserving Face Space (2013, methodology): “SVM) for classification [21, 10, 15]; (2) directly using class labels as supervision of deep models [6, 24].”
FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition (2016, background): “Average Accuracy Gabor + PCA [40] 80.2% Deep mPoT [41] 82.4% CDA+CCA [42] 85.0% disRBM [43] 85.4% bootstrap-recon [44] 86.8% Train From Scratch (BN) 82.5% VGG Fine-Tune (baseline) 86.7% FN2EN 88.9% well in recognizing fear and happy, while angry is the hardest expression, which is mostly confused…”
A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “Some of the work on analysis of the features to understand what is lost and what is captured during its training is demonstrated in [64], [79], [80].”
Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and Recognition (2015, background): “The most well-established paradigm for hierarchical representations is deep learning [111], [112].”
Facial Expression Recognition via a Boosted Deep Belief Network (2014, methodology): “To become more adaptable to the real world that consists of combination of edges, deep learning networks have been employed for the applications of facial expression recognition [20, 21].”
Learning Deep Face Representation (2014, background): “One direction is to automate the representation learning process by unsupervised learning algorithms [19, 20, 21].”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, methodology): “CNNs are used in [144], [145], [146], [147], [148].”
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization (2021, background): “Generative Models for Image Understanding: Our approach is in line with various works that explore the use of generative modeling in different forms for discriminative and image recognition tasks, an idea that dates back until at least [65] and has also been studied using early energybased models [7”