Learning hierarchical representations for face verification with convolutional deep belief networks

By Gary B. Huang, Honglak Lee, Eric Learned-Miller. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

430 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/922838dd98d599d1d229cc73896d55e7a769aa7c

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

Citations in the corpus

Deep Learning for Computer Vision: A Brief Review (2018, background): “However, a later variation of the DBN, the Convolutional Deep Belief Network (CDBN) ([42, 43]), uses the spatial information of neighboring pixels by introducing convolutional RBMs, thus producing a translation invariant generative model that successfully scales when it comes to high dimensional ima”
Multi-manifold deep metric learning for image set classification (2015, methodology): “Deep Learning: Recently, deep learning has attracted increasing interest in computer vision and machine learning, and a variety of deep learning algorithms have been proposed over the past few years [12, 14, 17, 20, 21].”
Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations (2014, methodology): “Deep learning methods, such as Boltzmann machine [9], sum product network [17], and deep neural net [16, 25, 22, 23, 24, 26] have been applied to face recognition.”
Learning Features and Parts for Fine-Grained Recognition (2014, background): “The recent success of convolutional neural networks [24], [25] on large-scale classification and face recognition [26], [27] demonstrates that powerful features can be learned directly from pixels.”
DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014, methodology): “[16] used as input LBP features and they showed improvement when combining with traditional methods.”
Labeled Faces in the Wild: A Survey (2016, methodology): “15 Learning Hierarchical Representations for Face Verification with Convolutional Deep Belief Networks, 2012 [48]”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “Unlike most existing studies [22, 5, 14, 47, 13] that rely on a single training data source, in order to take advantage of more data from multiple source-domains to improve the performance in the target-domain, we introduce the multi-task learning constraint to DGPLVM.”
Using deep learning to enhance cancer diagnosis and classication (2013, methodology): “Unsupervised feature learning methods and deep learning have been widely used for image and audio applications such as (Lee et al., 2009b; Huang et al., 2012), etc.”
Deeply learned face representations are sparse, selective, and robust (2014, background): “Face recognition achieved great progress thanks to extensive research effort devoted to this area [36, 30, 18, 14, 1, 6, 15, 26, 7, 5, 27, 31, 29, 32, 28].”
Visualizations of Deep Neural Networks in Computer Vision: A Survey (2017, methodology): “Huang [28] 2012 Architecture assessment Pixel displays Representation Learning CDBN LFW”
Learning Compact Binary Face Descriptor for Face Recognition (2015, methodology): “There have been extensive work on face representation in the literature, and these methods can be mainly classified into two categories: holistic feature representation [4], [56] and local feature representation [26], [36].”
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling (2013, neutral): “, [17, 11, 12]).”
Deep Learning Identity-Preserving Face Space (2013, methodology): “[10] introduced the convolutional restricted Boltzmann machine (CRBM), which incorporates local filters into RBM.”
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.”