Weakly Supervised Disentanglement by Pairwise Similarities

Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered (Locatello et al. 2018). Motivated by a real-world problem, we propose a setting where the user introduces weak supervision by providing similarities between instances based on a factor to be disentangled. The similarity is provided as either a binary (yes/no) or real-valued label describing whether a pair of instances are similar or not. We propose a new method for weakly supervised disentanglement of latent variables within the framework of Variational Autoencoder. Experimental results demonstrate that utilizing weak supervision improves the performance of the disentanglement method substantially.

[1]  Dacheng Tao,et al.  Dual Swap Disentangling , 2018, NeurIPS.

[2]  Alexei A. Efros,et al.  Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Michael I. Jordan,et al.  Information Constraints on Auto-Encoding Variational Bayes , 2018, NeurIPS.

[4]  Ludovic Denoyer,et al.  Multi-View Data Generation Without View Supervision , 2018, ICLR.

[5]  S. Stanojevic,et al.  Multi-ethnic reference values for spirometry for the 3–95-yr age range: the global lung function 2012 equations , 2012, European Respiratory Journal.

[6]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[7]  Jonathan Krause,et al.  3D Object Representations for Fine-Grained Categorization , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[8]  Xavier Binefa,et al.  Learning Disentangled Representations with Reference-Based Variational Autoencoders , 2019, ICLR 2019.

[9]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  F. Martinez,et al.  Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary. , 2007, American journal of respiratory and critical care medicine.

[11]  Bernhard Schölkopf,et al.  Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , 2018, ICML.

[12]  Luca Saglietti,et al.  Gaussian Process Prior Variational Autoencoders , 2018, NeurIPS.

[13]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Frank D. Wood,et al.  Learning Disentangled Representations with Semi-Supervised Deep Generative Models , 2017, NIPS.

[15]  Sebastian Nowozin,et al.  Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations , 2017, AAAI.

[16]  Roger B. Grosse,et al.  Isolating Sources of Disentanglement in Variational Autoencoders , 2018, NeurIPS.

[17]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[18]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[19]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[20]  Andriy Mnih,et al.  Disentangling by Factorising , 2018, ICML.