Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/koukyo1994/awesome-disentangled-representations

A curated list of papers on disentangled representation learning inspired by https://github.com/sootlasten/disentangled-representation-papers and https://github.com/matthewvowels1/Awesome-VAEs.
https://github.com/koukyo1994/awesome-disentangled-representations

List: awesome-disentangled-representations

awesome-list disentangled-representations disentanglement vae variational-autoencoder

Last synced: 16 days ago
JSON representation

A curated list of papers on disentangled representation learning inspired by https://github.com/sootlasten/disentangled-representation-papers and https://github.com/matthewvowels1/Awesome-VAEs.

Awesome Lists containing this project

README 

        
# Awesome Disentangled Representations



A curated list of papers on disentangled representation learning inspired by https://github.com/sootlasten/disentangled-representation-papers and https://github.com/matthewvowels1/Awesome-VAEs.



Since the original curated list([sootlasten/disentangled-representation-papers](https://github.com/sootlasten/disentangled-representation-papers)) seems to be stopped now, and I would like to add some summarization using GitHub issues, I decided not to fork the repository but make a new curated list.



To respect the original repository, I've added a tag(`[copied]`) in front of the name of the paper which was originally listed in [sootlasten/disentangled-representation-papers](https://github.com/sootlasten/disentangled-representation-papers). I also use the star(`☆`) and `?` notation to show the importance of the paper following the original repository. The judges of the original repository are remained, but `?` may be replaced by my judge.**`?` notation show that I haven't fully read the paper, and `☆` indicates the importance/quality of each paper (the larger the number of the stars, the better the importance/quality is)**.



## 2020



* ☆☆☆ Weakly-Supervised Disentanglement Without Compromises (Feb, Locatello et. al.) [[paper]](https://arxiv.org/abs/2002.02886) [[code]](https://github.com/google-research/disentanglement_lib/blob/master/disentanglement_lib/methods/weak/weak_vae.py)



## 2019



* ? On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset (Jun, Gondal et. al.) [[paper]](https://arxiv.org/abs/1906.03292)

* ? On the Fairness of Disentangled Representations (May, Locatello et. al.) [[paper]](https://arxiv.org/abs/1905.13662)

* ☆☆☆ Variational Autoencoders and Nonlinear ICA: A Unifying Framework (Jul, Khemakhem et. al.) [[paper]](https://arxiv.org/abs/1907.04809)

* ? Explicitly disentangling image content from translation and rotation with spatial-VAE (Sep, Bepler et. al.) [[paper]](https://arxiv.org/abs/1909.11663) [[code]](https://github.com/tbepler/spatial-VAE)

* ? `[copied]` Are Disentangled Representations Helpful for Abstract Visual Reasoning? (May, Steenkiste et. al.)[[paper]](https://arxiv.org/abs/1905.12506)



## 2018



* ? Discovering Interpretable Representations for Both Deep Generative and Discriminative Models (Jul, Adel et al.) [[paper]](http://proceedings.mlr.press/v80/adel18a.html)

* ? `[copied]` Hyperprior Induced Unsupervised Disentanglement of Latent Representations (Jan, Ansari and Soh) [[paper]](https://arxiv.org/abs/1809.04497)

* ? `[copied]` A Spectral Regularizer for Unsupervised Disentanglement (Dec, Ramesh et. al.) [[paper]](https://arxiv.org/abs/1812.01161v1)

* ? `[copied]` Disentangling Disentanglement  (Dec, Mathieu et. al.) [[paper]](https://arxiv.org/abs/1812.02833v1)

* ? `[copied]` Recent Advances in Autoencoder-Based Representation Learning (Dec, Tschannen et. al.) [[paper]](http://bayesiandeeplearning.org/2018/papers/151.pdf?fbclid=IwAR0AKPuAsCFFsTCJ52o6-BkJebR9UuURnesksd1wf5QfLvuU2LBetc7moKc)

* ? `[copied]` Visual Object Networks: Image Generation with Disentangled 3D Representation (Dec, Zhu et. al.) [[paper]](https://arxiv.org/abs/1812.02725v1)

* ? `[copied]` Towards a Definition of Disentangled Representations (Dec, Higgins et. al.) [[paper]](https://arxiv.org/pdf/1812.02230v1.pdf)

* ☆☆☆ `[copied]` Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations (Dec, Locatello et. al.) [[paper]](https://arxiv.org/abs/1811.12359v1) [[code]](https://github.com/google-research/disentanglement\_lib)

* ? `[copied]` Learning Deep Representations by Mutual Information Estimation and Maximization (Aug, Hjelm et. al.) [[paper]](https://arxiv.org/abs/1808.06670)

* ☆☆ `[copied]` Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies (Aug, Achille et. al.) [[paper]](https://arxiv.org/abs/1808.06508)

* ? `[copied]` Learning to Decompose and Disentangle Representations for Video Prediction (Hsieh et. al.) [[paper]](https://arxiv.org/abs/1806.04166)

* ? `[copied]` Insights on Representational Similarity in Neural Networks with Canonical Correlation (Jun, Morcos et. al.) [[paper]](https://arxiv.org/abs/1806.05759)

* ☆☆ `[copied]` Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects (Jun, Kosiorek et. al.) [[paper]](https://arxiv.org/abs/1806.01794)

* ☆☆☆ `[copied]` Neural Scene Representation and Rendering (Jun, Eslami et. al.) [[paper]](https://deepmind.com/research/publications/neural-scene-representation-and-rendering/)

* ? `[copied]` Image-to-image translation for cross-domain disentanglement (May, Gonzalez-Garcia et. al.) [[paper]](https://arxiv.org/abs/1805.09730)

* ☆ `[copied]` Learning Disentangled Joint Continuous and Discrete Representations (May, Dupont) [[paper]](https://arxiv.org/abs/1804.00104) [[code]](https://github.com/Schlumberger/joint-vae) [[summary-slide]](./summary-slides/dupont2018learning.pdf) [[thread]](https://github.com/koukyo1994/awesome-disentangled-representations/issues/1)

* ? `[copied]` DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis (Apr, Bem et. al.) [[paper]](https://arxiv.org/abs/1804.06364)

* ? `[copied]` Structured Disentangled Representations (Apr, Esmaeili et. al.) [[paper]](https://arxiv.org/abs/1804.02086)

* ☆☆ `[copied]` Understanding disentangling in β-VAE (Apr, Burgess et. al.) [[paper]](https://arxiv.org/abs/1804.03599)

* ? `[copied]` On the importance of single directions for generalization (Mar, Morcos et. al.) [[paper]](https://arxiv.org/abs/1803.06959)

* ☆☆ `[copied]` Unsupervised Representation Learning by Predicting Image Rotations (Mar, Gidaris et. al.) [[paper]](https://arxiv.org/abs/1803.07728)

* ? `[copied]` Disentangled Sequential Autoencoder (Mar, Li & Mandt) [[paper]](https://arxiv.org/abs/1803.02991)

* ☆☆☆ `[copied]` Isolating Sources of Disentanglement in Variational Autoencoders (Mar, Chen et. al.) [[paper]](https://arxiv.org/abs/1802.04942v2) [[code]](https://github.com/rtqichen/beta-tcvae)

* ☆☆ `[copied]` Disentangling by Factorising (Feb, Kim & Mnih) [[paper]](https://arxiv.org/abs/1802.05983)

* ☆☆ `[copied]` Disentangling the Independently Controllable Factors of Variation by Interacting with the World (Feb, Bengio's group) [[paper]](https://arxiv.org/abs/1802.09484)

* ? `[copied]` On the Latent Space of Wasserstein Auto-Encoders (Feb, Rubenstein et. al.) [[paper]](https://arxiv.org/abs/1802.03761)

* ? `[copied]` Auto-Encoding Total Correlation Explanation (Feb, Gao et. al.) [[paper]](https://arxiv.org/abs/1802.05822v1)

* ? `[copied]` Fixing a Broken ELBO (Feb, Alemi et. al.) [[paper]](https://arxiv.org/abs/1711.00464)

* ☆ `[copied]` Learning Disentangled Representations with Wasserstein Auto-Encoders (Feb, Rubenstein et. al.) [[paper]](https://openreview.net/forum?id=Hy79-UJPM)

* ? `[copied]` Rethinking Style and Content Disentanglement in Variational Autoencoders (Feb, Shu et. al.) [[paper]](https://openreview.net/forum?id=B1rQtwJDG)

* ? `[copied]` A Framework for the Quantitative Evaluation of Disentangled Representations (Feb, Eastwood & Williams) [[paper]](https://openreview.net/forum?id=By-7dz-AZ)



## 2017



* ? `[copied]` The β-VAE's Implicit Prior (Dec, Hoffman et. al.) [[paper]](http://bayesiandeeplearning.org/2017/papers/66.pdf)

* ☆☆ `[copied]` The Multi-Entity Variational Autoencoder (Dec, Nash et. al.) [[paper]](http://charlienash.github.io/assets/docs/mevae2017.pdf)

* ? `[copied]` Learning Independent Causal Mechanisms (Dec, Parascandolo et. al.) [[paper]](https://arxiv.org/abs/1712.00961)

* ? `[copied]` Variational Inference of Disentangled Latent Concepts from Unlabeled Observations (Nov, Kumar et. al.) [[paper]](https://arxiv.org/abs/1711.00848)

* ☆ `[copied]` Neural Discrete Representation Learning (Nov, Oord et. al.) [[paper]](https://arxiv.org/abs/1711.00937v2)

* ? `[copied]` Disentangled Representations via Synergy Minimization (Oct, Steeg et. al.) [[paper]](https://arxiv.org/abs/1710.03839v1)

* ? `[copied]` Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data (Sep, Hsu et. al.) [[paper]](https://arxiv.org/abs/1709.07902) [[code]](https://github.com/wnhsu/ScalableFHVAE)

* ☆ `[copied]` Experiments on the Consciousness Prior (Sep, Bengio & Fedus) [[paper]](https://ai-on.org/pdf/bengio-consciousness-prior.pdf)

* ☆☆ `[copied]` The Consciousness Prior (Sep, Bengio) [[paper]](https://arxiv.org/abs/1709.08568)

* ? `[copied]` Disentangling Motion, Foreground and Background Features in Videos (Jul, Lin. et. al.) [[paper]](https://imatge-upc.github.io/unsupervised-2017-cvprw/)

* ☆ `[copied]` SCAN: Learning Hierarchical Compositional Visual Concepts (Jul, Higgins. et. al.) [[paper]]( https://arxiv.org/abs/1707.03389)

* ☆☆☆ `[copied]` DARLA: Improving Zero-Shot Transfer in Reinforcement Learning (Jul, Higgins et. al.) [[paper]](https://arxiv.org/abs/1707.08475)

* ☆☆ `[copied]` Unsupervised Learning via Total Correlation Explanation (Jun, Ver Steeg) [[paper]](https://arxiv.org/abs/1706.08984) [[code]](https://github.com/gregversteeg/CorEx)

* ? `[copied]` PixelGAN Autoencoders (Jun, Makhzani & Frey) [[paper]](https://arxiv.org/abs/1706.00531)

* ? `[copied]` Emergence of Invariance and Disentanglement in Deep Representations (Jun, Achille & Soatto) [[paper]](https://arxiv.org/abs/1706.01350)

* ☆☆ `[copied]` A Simple Neural Network Module for Relational Reasoning (Jun, Santoro et. al.) [[paper]](https://arxiv.org/abs/1706.01427)

* ? `[copied]` Learning Disentangled Representations with Semi-Supervised Deep Generative Models  (Jun, Siddharth, et al.)  [[paper]](https://arxiv.org/abs/1706.00400)

* ? `[copied]` Unsupervised Learning of Disentangled Representations from Video (May, Denton & Birodkar) [[paper]](https://arxiv.org/abs/1705.10915)

* ? Multi-Level Variational Autoencoder: Learning Disentangled representations from Grouped Observations (May, Bouchacourt et. al.) [[paper]](https://arxiv.org/abs/1705.08841) [[code]](https://github.com/ananyahjha93/multi-level-vae)



## 2016



* ☆☆ `[copied]` Deep Variational Information Bottleneck (Dec, Alemi et. al.) [[paper]](https://arxiv.org/abs/1612.00410)

* ☆☆☆ `[copied]` β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (Nov, Higgins et. al.) [[paper]](https://openreview.net/forum?id=Sy2fzU9gl) [[code]](https://github.com/sootlasten/beta-vae)

* ? `[copied]` Disentangling factors of variation in deep representations using adversarial training (Nov, Mathieu et. al.) [[paper]](https://arxiv.org/abs/1611.03383)

* ☆☆ `[copied]` Information Dropout: Learning Optimal Representations Through Noisy Computation (Nov, Achille & Soatto) [[paper]](https://arxiv.org/abs/1611.01353)

* ☆☆ `[copied]` InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (Jun, Chen et. al.) [[paper]](https://arxiv.org/abs/1606.03657)

* ☆☆☆ `[copied]` Attend, Infer, Repeat: Fast Scene Understanding with Generative Models (Mar, Eslami et. al.) [[paper]](https://arxiv.org/abs/1603.08575?context=cs)

* ☆☆☆ `[copied]` Building Machines That Learn and Think Like People (Apr, Lake et. al.) [[paper]](https://arxiv.org/abs/1604.00289)

* ☆ `[copied]` Understanding Visual Concepts with Continuation Learning (Feb, Whitney et. al.) [[paper]](https://arxiv.org/abs/1602.06822)

* ? `[copied]` Disentangled Representations in Neural Models (Feb, Whitney) [[paper]](https://arxiv.org/abs/1602.02383v1)



## Older works



* ☆☆ `[copied]` Deep Convolutional Inverse Graphics Network (2015, Kulkarni et. al.) [[paper]](https://arxiv.org/abs/1503.03167)

* ? `[copied]` Learning to Disentangle Factors of Variation with Manifold Interaction (2014, Reed et. al.) [[paper]](http://proceedings.mlr.press/v32/reed14.pdf)

* ☆☆☆ `[copied]` Representation Learning: A Review and New Perspectives (2013, Bengio et. al.) [[paper]](https://arxiv.org/abs/1206.5538?context=cs)

* ? `[copied]` Disentangling Factors of Variation via Generative Entangling (2012, Desjardinis et. al.) [[paper]](https://arxiv.org/abs/1210.5474)

* ☆☆☆ `[copied]` Transforming Auto-encoders (2011, Hinton et. al.) [[paper]](https://www.cs.toronto.edu/~fritz/absps/transauto6.pdf)

* ☆☆ `[copied]` Learning Factorial Codes By Predictability Minimization (1992, Schmidhuber) [[paper]](https://www.mitpressjournals.org/doi/pdf/10.1162/neco.1992.4.6.863)

* ☆☆☆ `[copied]` Self-Organization in a Perceptual Network (1988, Linsker) [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=36)

* ☆☆ Semi-supervised Learning with Deep Generative Models (2014, Kingma et. al.) [[paper]](https://arxiv.org/abs/1406.5298) [[code]](http://github.com/dpkingma/nips14-ssl)



## Talks



* `[copied]` Building Machines that Learn & Think Like People (2018, Tenenbaum) [[youtube]](https://www.youtube.com/watch?v=RB78vRUO6X8&t=1807s)

* `[copied]` From Deep Learning of Disentangled Representations to Higher-level Cognition (2018, Bengio) [[youtube]](https://www.youtube.com/watch?v=Yr1mOzC93xs)

* `[copied]` What is wrong with convolutional neural nets? (2017, Hinton) [[youtube]](https://www.youtube.com/watch?v=rTawFwUvnLE&t=2152s)