Robust Boltzmann Machines for recognition and denoising

By Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton. 2012

184 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Unsupervised Feature Learning via Non-parametric Instance Discrimination (2018, methodology): “Classical generative models include Restricted Bolztmann Machines (RBMs) [12, 39, 21], and Autoencoders [40, 20].”
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, background): “Bolztmann Machines (RBMs) [24, 40], Auto-encoders [20, 42] and generative adversarial network (GAN) [7, 10, 11] are widely studied.”
Unsupervised Learning of Visual Representations Using Videos (2015, background): “The third class of algorithms and more related to our paper is unsupervised learning of visual representations from the pixels themselves using deep learning approaches [21, 26, 44, 39, 29, 47, 9, 33, 2, 49, 8].”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, background): “d models or 2.1D representations of images have been studied in the context of moving or still object segmentation [38,23,39,41,11]. The layered structure is introduced into generative image modeling [20,35]. Tang et al. [35] modeled the occluded images with gated restricted Boltzmann machines and a”
Tagger: Deep Unsupervised Perceptual Grouping (2016, background): “Many of the works in that area [16, 32, 29, 11] build upon Restricted Boltzmann Machines.”
Transitive Invariance for Self-Supervised Visual Representation Learning (2017, methodology): “Earlier methods for generative models include Anto-Encoders [38, 51, 31, 29] and Restricted Boltzmann Machines (RBMs) [23, 4, 49, 12].”
Learning to Relate Images (2011, neutral): “22.”
Deeply learned face representations are sparse, selective, and robust (2014, methodology): “[29] proposed Robust Boltzmann Machine to distinguish corrupted pixels and learn latent representations.”
Unsupervised Deep Learning by Neighbourhood Discovery (2019, methodology): “The most commonly used and efﬁcient generative models include Restricted Boltzmann Machines (Lee et al., 2009; Hinton et al., 2006; Tang et al., 2012), Autoencoders (Ng, 2011; Vincent et al., 2010), and Generative Adversarial Networks (Radford et al., 2016; Goodfellow et al., 2014).”
Unsupervised Person Re-Identification via Multi-Label Classification (2020, methodology): “Classical generative models include Restricted Bolztmann Machines (RBM) (Hinton et al., 2006; Tang et al., 2012), and auto-encoder (Vincent et al.”
Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines (2013, background): “The robust Boltzmann machine (RoBM) (Tang et al., 2012) shares its motivation with our work, though there are several technical differences.”
Wasserstein Training of Restricted Boltzmann Machines (2016, methodology): “Denoising highly corrupted complex data will however require to combine Wasserstein models with more flexible noise models such as the ones proposed by [17].”
Minerva: A Scalable and Highly Efficient Training Platform for Deep Learning (2014, background): “The success of deep learning and the great amount of remaining puzzles inspire new algorithmic innovations in this space, deriving models that sometimes depart significantly from a straightforward feedforward network topology [1, 2, 3].”
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis (2013, methodology): “The subsequent methods [21, 20, 18, 16] overcame this problem by learning noise models from training data.”
Training Restricted Boltzmann Machines (2015, background): “, 2011; Kivinen and Williams, 2012), or to solve inpainting tasks (Kivinen and Williams, 2012; Tang et al., 2012) by sampling the missing or deteriorated parts of a given image from the distribution.”
Bidirectional Helmholtz Machines (2015, methodology): “If the training data consists of, for example, images, it can be used to generate textures from these images, or to solve inpainting tasks by sampling the missing or deteriorated parts of a given image from the distribution [16, 50, 62, 104].”