Filters








563 Hits in 4.4 sec

Variational Inference of Disentangled Latent Concepts from Unlabeled Observations [article]

Abhishek Kumar, Prasanna Sattigeri, Avinash Balakrishnan
<span title="2018-12-27">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We consider the problem of unsupervised learning of disentangled representations from large pool of unlabeled observations, and propose a variational inference based approach to infer disentangled latent  ...  We introduce a regularizer on the expectation of the approximate posterior over observed data that encourages the disentanglement.  ...  CONCLUDING REMARKS We proposed a principled variational framework to infer disentangled latents from unlabeled observations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.00848v3">arXiv:1711.00848v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w5yh22klqzfi5b2nldrhuzy6oi">fatcat:w5yh22klqzfi5b2nldrhuzy6oi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930132018/https://arxiv.org/pdf/1711.00848v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1e/3f/1e3fa91a0cc4fb97a981a3b8b58d6b1a20c9640f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.00848v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Disentangled Relational Representations for Explaining and Learning from Demonstration [article]

Yordan Hristov, Daniel Angelov, Michael Burke, Alex Lascarides, Subramanian Ramamoorthy
<span title="2019-10-06">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a method in which a learning agent utilizes the information bottleneck layer of a high-parameter variational neural model, with auxiliary loss terms, in order to ground abstract concepts such  ...  We evaluate the properties of the latent space of the learned model in a photorealistic synthetic environment and particularly focus on examining its usability for downstream tasks.  ...  Acknowledgments This work is partly supported by funding from the Turing Institute, as part of the Safe AI for surgical assistance project  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13627v2">arXiv:1907.13627v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r5lddkk2gzd5fovhapi5s2hdri">fatcat:r5lddkk2gzd5fovhapi5s2hdri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200726131510/https://arxiv.org/pdf/1907.13627v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13627v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Disentangled Representations with Reference-Based Variational Autoencoders [article]

Adria Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek
<span title="2019-01-24">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others.  ...  Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks.  ...  Variational inference of disentangled latent concepts from unlabeled observations. ICLR, 2018. Larsen, A. B. L., Sønderby, S. K., Larochelle, H., and Winther, O.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08534v1">arXiv:1901.08534v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q3fbok6nuff2joeipjpdwrnida">fatcat:q3fbok6nuff2joeipjpdwrnida</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929070650/https://arxiv.org/pdf/1901.08534v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fe/9b/fe9b0accf0e7d3821bc5d7d62937499a441633c9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.08534v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Latent Variable Modeling for Generative Concept Representations and Deep Generative Models [article]

Daniel T. Chang
<span title="2018-12-26">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Latent representations are the essence of deep generative models and determine their usefulness and power.  ...  For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things.  ...  The Disentangled Inferred Prior VAE (DIP-VAE) [14] is a principled variational framework for inferring disentangled latent variables from unlabeled observations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.11856v1">arXiv:1812.11856v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zsqsvtrt3rgjbdnwpvnvnd5aki">fatcat:zsqsvtrt3rgjbdnwpvnvnd5aki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930141824/https://arxiv.org/ftp/arxiv/papers/1812/1812.11856.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8e/62/8e629e93a525797ce7f5e704c0dda8f42029451b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.11856v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

JADE: Joint Autoencoders for Dis-Entanglement [article]

Ershad Banijamali, Amir-Hossein Karimi, Alexander Wong, Ali Ghodsi
<span title="2017-11-24">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we present a novel method for disentangling factors of variation in data-scarce regimes.  ...  Specifically, we explore the application of feature disentangling for the problem of supervised classification in a setting where few labeled samples exist, and there are no unlabeled samples for use in  ...  To assert that the JADE setup is indeed disentangling variation factors, we conduct the following simple experiment: observe the variation in latent space values as different types of samples are passed  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.09163v1">arXiv:1711.09163v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4hxefk7chfcblfpl6hecwjdvu4">fatcat:4hxefk7chfcblfpl6hecwjdvu4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912135532/https://arxiv.org/pdf/1711.09163v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4a/dd/4addf57cf1512a5d463dda257ec72b4b9ed42899.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.09163v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Disentangling Action Sequences: Discovering Correlated Samples [article]

Jiantao Wu, Lin Wang
<span title="2020-10-17">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We further introduce the concept of disentangling action sequences which facilitates the description of the behaviours of the existing disentangling approaches.  ...  We demonstrate the data itself, such as the orientation of images, plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with  ...  Notion the conception of disentangling factors of variation is first proposed in 2013.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11684v1">arXiv:2010.11684v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cndbrw2htnh3vo5uvm3epcwlfm">fatcat:cndbrw2htnh3vo5uvm3epcwlfm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029030047/https://arxiv.org/pdf/2010.11684v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/74/35/7435d5f1130e05f079dafbc821eab0911a6ce7d2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11684v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild [article]

Aviv Gabbay, Niv Cohen, Yedid Hoshen
<span title="2021-10-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While annotating the true generative factors is only required for a limited number of observations, we argue that it is infeasible to enumerate all the factors of variation that describe a real-world image  ...  As an alternative approach, recent methods rely on limited supervision to disentangle the factors of variation and allow their identifiability.  ...  Variational inference of disentangled latent concepts from unlabeled observations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15610v2">arXiv:2106.15610v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/242rvtvzjrh6zf7tmvvbmaglxm">fatcat:242rvtvzjrh6zf7tmvvbmaglxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210701092701/https://arxiv.org/pdf/2106.15610v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/33/0d/330dac37a7d661ad8b2861810adc008b30864893.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15610v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Scaling-up Disentanglement for Image Translation [article]

Aviv Gabbay, Yedid Hoshen
<span title="2021-09-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
: Learning disentangled representations with latent optimization.  ...  In this work, we propose OverLORD, a single framework for disentangling labeled and unlabeled attributes as well as synthesizing high-fidelity images, which is composed of two stages; (i) Disentanglement  ...  Introduction Learning disentangled representations for different factors of variation in a set of observations is a fundamental problem in machine learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.14017v2">arXiv:2103.14017v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r3sinwhijbadvamkpvq7rndgay">fatcat:r3sinwhijbadvamkpvq7rndgay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210914155541/https://arxiv.org/pdf/2103.14017v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9d/79/9d795f3f39b77beda6081dd12fc2fdf8b02f4cbc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.14017v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Early Visual Concept Learning with Unsupervised Deep Learning [article]

Irina Higgins, Loic Matthey, Xavier Glorot, Arka Pal, Benigno Uria, Charles Blundell, Shakir Mohamed, Alexander Lerchner
<span title="2016-09-20">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Automated discovery of early visual concepts from raw image data is a major open challenge in AI research.  ...  Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation.  ...  We aim to maximise the probability of the observed data x on average over all possible samples from the latent factors z.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.05579v3">arXiv:1606.05579v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/org54dkpgje2xdtss4bt5qtekm">fatcat:org54dkpgje2xdtss4bt5qtekm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001011449/https://arxiv.org/pdf/1606.05579v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d8/f0/d8f0801362881a44d85296084048d0bbe51fea7f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.05579v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods [article]

Guo-Jun Qi, Jiebo Luo
<span title="2021-01-02">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
nets (GANs) and other deep networks by exploring the distribution of unlabeled data for more powerful representations.  ...  We will review the principles of learning the transformation equivariant, disentangled, self-supervised and semi-supervised representations, all of which underpin the foundation of recent progresses.  ...  It compiles the graphical model for modeling a general dependency on observed and unobserved latent variables with neural networks, and a stochastic computation graph [91] is used to infer with and train  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.11260v2">arXiv:1903.11260v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hjya3ojzmfh7nnldhqkdx6o37a">fatcat:hjya3ojzmfh7nnldhqkdx6o37a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929025312/https://arxiv.org/pdf/1903.11260v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/64/90/64904e0a9ee10d513836e5fe0a875fbdd8b92d79.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.11260v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations [article]

Jan Stühmer, Richard E. Turner, Sebastian Nowozin
<span title="2019-09-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We first show that these modifications, e.g. beta-VAE, simplify the tendency of variational inference to underfit causing pathological over-pruning and over-orthogonalization of learned components.  ...  Second, we demonstrate that the proposed prior encourages a disentangled latent representation which facilitates learning of disentangled representations.  ...  Balakrishnan, "Variational inference of disentangled latent concepts from unlabeled observations," arXiv preprint arXiv:1711.00848, 2017. [12] R. Vedantam, I. Fischer, J. Huang, and K.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05063v1">arXiv:1909.05063v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hzmnqzoy5bc4pcw4su2ndwdha4">fatcat:hzmnqzoy5bc4pcw4su2ndwdha4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902130220/https://arxiv.org/pdf/1909.05063v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1b/08/1b0848218d23e79e7947b52052e887b52139ea9f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05063v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Interpretable Latent Spaces for Learning from Demonstration [article]

Yordan Hristov, Alex Lascarides, Subramanian Ramamoorthy
<span title="2018-10-02">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a method which utilises the grouping of user-defined symbols and their corresponding sensory observations in order to align the learnt compressed latent representation with the semantic notions  ...  Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in  ...  We report F1 scores for each class label, per concept group, including predictions for unlabelled observations which represent both known and unknown labels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.06583v2">arXiv:1807.06583v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w3pyvgyzffgaplqgakpgwlfejy">fatcat:w3pyvgyzffgaplqgakpgwlfejy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903054945/https://arxiv.org/pdf/1807.06583v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/18/74/18742f93a6c5e6b06a016a35b4b4a86f1377348e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.06583v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets [article]

Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel
<span title="2016-06-12">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation.  ...  Specifically, InfoGAN successfully disentangles writing styles from digit shapes on the MNIST dataset, pose from lighting of 3D rendered images, and background digits from the central digit on the SVHN  ...  Since DC-IGN requires supervision, it was previously not possible to learn a latent code for a variation that's unlabeled and hence salient latent factors of variation cannot be discovered automatically  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.03657v1">arXiv:1606.03657v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fypmdkxwsbg6fbwgfaznlu2b6u">fatcat:fypmdkxwsbg6fbwgfaznlu2b6u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200917130921/https://arxiv.org/pdf/1606.03657v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/65/e2/65e2b888ba515d6ad6d1b96fa25c146c4d7499c7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.03657v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Disentangled Sequence Clustering for Human Intention Inference [article]

Mark Zolotas, Yiannis Demiris
<span title="2022-02-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Though unlike previous frameworks for disentanglement, the proposed variant also infers a discrete variable to form a latent mixture model and enable clustering of global sequence concepts, e.g. intentions  ...  from observed human behaviour.  ...  Acknowledgements This research was supported by an EPSRC Doctoral Training Award to Mark Zolotas and a Royal Academy of Engineering Chair in Emerging Technologies to Yiannis Demiris.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.09500v3">arXiv:2101.09500v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2jr7jaqzxbf5nnecsgavylshsi">fatcat:2jr7jaqzxbf5nnecsgavylshsi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211215181306/https://arxiv.org/pdf/2101.09500v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/69/c7/69c73da7070a61f5ba01473fc4439833efdb8b30.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.09500v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Identifiable Double VAE For Disentangled Representations [article]

Graziano Mita, Maurizio Filippone, Pietro Michiardi
<span title="2021-02-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE).  ...  ., AISTATS, 2020 suggest that employing a particular form of factorized prior, conditionally dependent on auxiliary variables complementing input observations, can be one such bias, resulting in an identifiable  ...  Such posterior is then used as a prior on the latent variables of a generative model, whose inference network learns a mapping between input observations and latents.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09360v2">arXiv:2010.09360v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pmzp26j7cfgrzip4dgttefjd7i">fatcat:pmzp26j7cfgrzip4dgttefjd7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201022204648/https://arxiv.org/pdf/2010.09360v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/48/b1/48b18bf5c9cad0e4c36b2d885f380c5c637e1a09.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09360v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 563 results