Learning to Disentangle Factors of Variation with Manifold Interaction

By Scott E. Reed, Kihyuk Sohn, Yuting Zhang, Honglak Lee. 2014

254 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016, background): “disBM [21] is a higher-order Boltzmann machine which learns a disentangled representation by “clamping” a part of the hidden units for a pair of data points that are known to match in all but one factors of variation.”
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, background): “Given that unsupervised algorithms did not initially perform well on realistic settings most of the other works have considered some more or less explicit form of supervision (Reed et al., 2014; Zhu et al., 2014; Yang et al., 2015; Kulkarni et al., 2015; Cheung et al., 2014; Mathieu et al., 2016; Na”
Learning to generate chairs with convolutional neural networks (2014, methodology): “Examples include: gated conditional RBMs [22] for modeling image transformations, training RBMs to disentangle face identity and pose information using conditional RBMs [24], and learning a generative model of digits conditioned on digit class using variational autoencoders [16].”
Generative Adversarial Text to Image Synthesis (2016, methodology): “Deep networks have been shown to learn representations in which interpolations between embedding pairs tend to be near the data manifold (Bengio et al., 2013; Reed et al., 2014).”
Action-Conditional Video Prediction using Deep Networks in Atari Games (2015, neutral): “This result implies that our model learns to distinguish between controlled objects and uncontrolled objects and transform them using disentangled representations (see [25, 24, 37] for related work on disentangling factors of variation).”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, background): “Reed et al. [31] introduced a disentan-gling Boltzmann machine to learn factors of variation such as pose or expression from identity for face images by exploiting higher-order manifold interactions.”
Weakly-Supervised Disentanglement Without Compromises (2020, background): “Initially, the community focused on more or less explicit and task dependent supervision (Reed et al., 2014; Yang et al., 2015; Kulkarni et al., 2015; Cheung et al., 2014; Mathieu et al., 2016; Narayanaswamy et al., 2017).”
On the Fairness of Disentangled Representations (2019, background): “[77, 15, 66, 70, 50, 52, 1] assume partially observed factors of variation that should be disentangled from the other unobserved ones.”
Are Disentangled Representations Helpful for Abstract Visual Reasoning? (2019, background): “Due to the initial poor performance of purely unsupervised methods, the field initially focused on semi-supervised [62, 11, 57, 58, 44, 46] and weakly supervised approaches [31, 12, 40, 21, 78, 20, 15, 35, 80, 54, 47, 64, 8].”
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (2018, background): “…did not initially perform well on realistic settings most of the other works have considered some more or less explicit form of supervision (Reed et al., 2014; Zhu et al., 2014; Yang et al., 2015; Kulkarni et al., 2015; Cheung et al., 2015; Mathieu et al., 2016; Narayanaswamy et al., 2017;…”
Disentangling by Factorising (2018, background): “…or explicit knowledge about the true underlying factors of the data have excelled at disentangling (Kulkarni et al., 2015; Kingma et al., 2014; Reed et al., 2014; Siddharth et al., 2017; Hinton et al., 2011; Mathieu et al., 2016; Goroshin et al., 2015; Hsu et al., 2017; Denton & Birodkar,…”
Learning Deep Disentangled Embeddings with the F-Statistic Loss (2018, methodology): “instances partitioned by factor value (Reed et al., 2014; Kingma et al., 2014; Kulkarni et al., 2015; Karaletsos et al., 2015; Reed et al., 2015).”
Theory and Evaluation Metrics for Learning Disentangled Representations (2019, methodology): “This “clamping” strategy was also applied in [33] to improve the disentanglement capability of a higher-order Boltzman Machine.”
Towards a Definition of Disentangled Representations (2018, background): “However, many other approaches [50, 23, 66, 63, 80, 78, 36, 17, 77, 46] and a recent disentanglement metric by [65] consider it perfectly ﬁne for each data generative factor to be encoded by multiple latent dimensions.”
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations (2017, background): “Much of the earlier work assumes some sort of supervision in terms of: (i) partial or full access to the generative factors per instance (Reed et al., 2014; Yang et al., 2015; Kulkarni et al., 2015; Karaletsos et al., 2015), (ii) knowledge about the nature of generative factors (e.g, translation,…”
Understanding disentangling in β-VAE (2018, background): “Most initial attempts to learn disentangled representations required supervised knowledge of the data generative factors [18, 35, 32, 44, 43, 12, 24, 7, 42, 20].”
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning (2017, background): “…learning (Schmidhuber, 1992; Desjardins et al., 2012; Cohen & Welling, 2014; 2015; Kulkarni et al., 2015; Hinton et al., 2011; Rippel & Adams, 2013; Reed et al., 2014; Yang et al., 2015; Goroshin et al., 2015; Kulkarni et al., 2015; Cheung et al., 2015; Whitney et al., 2016; Karaletsos et al.,…”
Disentangling factors of variation in deep representation using adversarial training (2016, background): “It is seldom the case that one has access to rich forms of labeled data in which the nature of these influences is given explicitly.”
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision (2016, background): “[15] showed that a disentangled hidden unit representations of Boltzmann Machines (disBM) could be learned based on the transformations on data manifold.”
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis (2015, methodology): “The disentangling Boltzmann Machine (disBM) [22] applies this idea to augment the Restricted Boltzmann Machine by partitioning its hidden state into distinct factors of variation and modeling their higher-order interaction.”