Autoencoders, Manifolds and Representations

Papers

• Adversarial Autoencoders (2018), Alireza Makhzani [pdf]
• Generative Adversarial Autoencoder Networks (2018), Ngoc-Trung Tran [pdf]
• Learning Sparse Latent Representations With the Deep Copula Information Bottleneck (2018), Aleksander Wieczorek, Mario Wieser [pdf]
• Mapping a Manifold of Perceptual Observations [pdf]
• On the Latent Space of Wasserstein Auto-Encoders (2018), Paul Rubenstein [pdf]
• Progressive Growing of GANs for Improved Quality, Stability, and Variation (2018), Samuli Laine [pdf]
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018), Richard Zhang [pdf]
• Variational Inference: A Review for Statisticians (2018), David M. Blei [pdf]
• Wasserstein Auto-Encoders (2018), Ilya Tolstikhin [pdf]
• Adversarially Regularized Autoencoders (2017), Junbo Zhao [pdf]
• beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (2017), Irina Higgins [pdf]
• Disentangling by Factorising (2017), Hyunjik Kim [pdf]
• Disentangled VAE for Image Classification - CS231n (2017), Chris Varano [pdf]
• InfoVAE: Information Maximizing Variational Autoencoders (2017), Shengjia Zhao [pdf]
• JADE: Joint Autoencoders for Dis-Entanglement (2017), Amir-Hossein Karimi [pdf]
• Learning Disentangled Representations from Grouped Observations (2017), Diane Bouchacourt [pdf]
• Learning Robust Features with Incremental Auto-Encoders (2017), Donghui Wang [pdf]
• Optimizing The Latent Space of Generative Networks (2017), Armand Joulin [pdf]
• PixelGAN Autoencoders (2017), Alireza Makhzani [pdf]
• Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders (2017), Momchil Peychev [pdf]
• Understanding Disentangling in beta-VAE (2017), Christopher P. Burgess [pdf]
• An Uncertain Future: Forecasting from Static Images using Variational Autoencoders (2016), Jacob Walker [pdf]
• Attribute2Image: Conditional Image Generation from Visual Attributes (2016), Xinchen Yan [pdf]
• Autoencoding beyond pixels using a learned similarity metric (2016), Anders Larsen [pdf]
• Early Visual Concept Learning with Unsupervised Deep Learning (2016), Irina Higgins [pdf]
• Generative Visual Manipulation on the Natural Image Manifold (2016), Jun-Yan Zhu [pdf]
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016), Xi Chen [pdf]
• Manifold Regularized Deep Neural Networks using Adversarial Examples (2016), Taehoon Lee [pdf]
• Semantic Facial Expression Editing using Autoencoded Flow (2016), Raymond Yeh [pdf]
• Spatial Transformer Networks (2016), Max Jaderberg [pdf]
• Tutorial on Variational Autoencoders (2016), Carl Doersch [pdf]
• Unsupervised Cross-Domain Image Generation (2016), Yaniv Taigman [pdf]
• Deep Convolutional Inverse Graphics Network (2015), Tejas Kulkarni, Will Whitney [pdf]
• Auto-encoding Variational Bayes (2014), Kingma [pdf]
• Representation Learning: A Review and New Perspectives (2014), Yoshua Bengio [pdf]
• What Regularized Auto-Encoders Learn from the Data Generating Distribution (2014), Guillaume Alain and Yoshua Bengio [pdf]
• Contractive Auto-Encoders (2011), Salah Rifai [pdf]
• A Tutorial on Energy-Based Learning (2006), Yann LeCun [pdf]

Blogs

• Introduction to Autoencoders (2018), Jeremy Jordan [Link]
• Intuitively Understanding Variational Autoencoders (2018), Irhum Shafkat [Link]
• Variational Autoencoders (2018), Jeremy Jordan [Link]
• Neural Networks, Manifolds, and Topology (2014), Christopher Olah [Link]

Videos

• From Deep Learning of Disentangled Representations to Higher-level Cognition [YouTube]
• Information Theory of Deep Learning [YouTube]
• The Sparse Manifold Transform [YouTube]

Libraries

• Disentangled Variational Autoencoders in PyTorch [GitHub]