Transforming Auto-Encoders

By Geoffrey E. Hinton, Alex Krizhevsky, Sida I. Wang. 2011

1,339 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Geology, Industrial and Manufacturing Engineering, Generative Models, Model Architectures

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 Geology

In Industrial and Manufacturing Engineering

In Generative Models

In Model Architectures

Citations in the corpus

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, background): “(Hinton et al., 2011; Cohen and Welling, 2014a) assume some knowledge of the effect of the factors of variations even though they are not observed.”
Spatial Transformer Networks (2015, background): “In this section we discuss the prior work related to the paper, covering the central ideas of modelling transformations with neural networks [12, 13, 27], learning and analysing transformation-invariant representations [3, 5, 8, 17, 19, 25], as well as attention and detection mechanisms for feature ”
Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, background): “More broadly, the problem of modelling data transformation has received significant attention in deep learning, one example being the transforming autoencoder [26].”
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images (2015, background): “This includes the development of transforming auto-encoders [28] and recent probabilistic models for images[29, 30].”
Representation Learning: A Review and New Perspectives (2012, background): “[85]) rather than by a single scalar and that these groups tend to move together.”
Learning to See by Moving (2015, background): “Another piece of work by [29] considers modeling spatial transformations us-ing boltzmann machines but did not assess the utility learnt features for performing visual tasks.”
Learning Image Representations Tied to Ego-Motion (2015, methodology): “Methods to learn representations with disentangled latent factors [11, 14] aim to sort properties like pose, illumination etc.”
Deep Convolutional Inverse Graphics Network (2015, methodology): “[10] ( transforming autoen-coders ) and Tieleman [27] which uses a domain speciﬁc decoder to reconstruct input images. x in batch Our work is similar in spirit to these works but has some key differences: (a) It uses a very generic convolutional architecture in the encoder and decoder networks to…”
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “Let us take Capsule Networks (Sabour et al., 2017) and the Slot Attention module (Locatello et al., 2020) in the computer vision field as examples: these modules try to create object-centric and part-centric representations inside the latent space of the network.”
Spatially Transformed Adversarial Examples (2018, methodology): “Modeling geometric transformation with neural networks was ﬁrst explored by “capsules,” computational units that locally transform their input for modeling 2D and 3D geometric changes (Hinton et al., 2011).”
Towards Deep Neural Network Architectures Robust to Adversarial Examples (2014, methodology): “For example, explicitly learning instantiation parameters as previously attempted by models such as Transforming Autoencoder Hinton et al. (2011).”
Dynamic Routing Between Capsules (2017, methodology): “Parse trees are generally constructed on the fly by dynamically allocating memory, but, following Hinton et al. [2000a], we shall assume that, for a single fixation, a parse tree is carved out of a fixed multilayer neural network like a sculpture is carved from a rock.”
On the Binding Problem in Artificial Neural Networks (2020, background): “The main example of category slots are capsules (Hinton et al., 2011, 2018), although other approaches such as Recurrent Entity Networks (Henaff et al., 2017) can also be viewed from this perspective.”
On the Fairness of Disentangled Representations (2019, methodology): “Weaker forms of supervision like relational information or additional assumptions on the effect of the factors of variation were also studied [39, 16, 47, 31, 91, 26, 19, 41, 93, 62, 53, 81, 8] and applied in the sequential data and reinforcement learning settings [88, 85, 57, 69, 37, 38].”
Are Disentangled Representations Helpful for Abstract Visual Reasoning? (2019, neutral): “Due to the initial poor performance of purely unsupervised methods, the ﬁeld initially focused on semi-supervised [60, 11, 55, 56, 43, 45] and weakly supervised approaches [31, 12, 40, 21, 75, 20, 15, 35, 77, 52, 46, 62, 8].”
An overview of deep learning in medical imaging focusing on MRI (2018, neutral): “There are new ways of constructing more data-efficient deep neural networks on the horizon, for example by encoding more domain-specific elements in the neural network structure as in the capsule systems of [340,341], which adds viewpoint invariance.”