2020

When and How Can Deep Generative Models be Inverted?

Aberdam, Aviad, Simon, Dror, Elad, Michael

Understand

Deep generative models (e.g.

GANs and VAEs) have been developed quite extensively in recent years.
Lately, there has been an increased interest in the inversion of such a model, i.e.
given a (possibly corrupted) signal, we wish to recover the latent vector that generated it.

Built on

Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ 1 \ell_{1} minimization
David L Donoho and Michael Elad · 2003
Earlier work this paper cites.
Just relax: Convex programming methods for identifying sparse signals in noise
Joel A Tropp · 2006
Earlier work this paper cites.
A fast iterative shrinkage-thresholding algorithm for linear inverse problems
Amir Beck and Marc Teboulle · 2009
Earlier work this paper cites.
Sparse and redundant representations: from theory to applications in signal and image processing
Michael Elad · 2010
Earlier work this paper cites.
Distributed optimization and statistical learning via the alternating direction method of multipliers
Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein · 2011
Earlier work this paper cites.
Auto-encoding variational bayes
Original
Diederik P Kingma and Max Welling · 2013
Earlier work this paper cites.
Generative adversarial nets
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio · 2014
Earlier work this paper cites.
Adversarial feature learning
Original
Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell · 2016
Earlier work this paper cites.
Maximal sparsity with deep networks?
Bo Xin, Yizhou Wang, Wen Gao, David Wipf, and Baoyuan Wang · 2016
Earlier work this paper cites.
Generative visual manipulation on the natural image manifold
Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, and Alexei A Efros · 2016
Earlier work this paper cites.

Similar

First-order methods in optimization
Amir Beck · 2017
Cited alongside, same era.
Compressed sensing using generative models
Ashish Bora, Ajil Jalal, Eric Price, and Alexandros G Dimakis · 2017
Cited alongside, same era.
Convolutional neural networks analyzed via convolutional sparse coding
Vardan Papyan, Yaniv Romano, and Michael Elad · 2017
Cited alongside, same era.
Phase retrieval under a generative prior
Paul Hand, Oscar Leong, and Vlad Voroninski · 2018
Cited alongside, same era.
A provably convergent scheme for compressive sensing under random generative priors
Original
Wen Huang, Paul Hand, Reinhard Heckel, and Vladislav Voroninski · 2018
Cited alongside, same era.
Spectral normalization for generative adversarial networks
Original
Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida · 2018
Cited alongside, same era.
Plu: The piecewise linear unit activation function
Original
Andrei Nicolae · 2018
Cited alongside, same era.
Solving linear inverse problems using gan priors: An algorithm with provable guarantees
Viraj Shah and Chinmay Hegde · 2018
Cited alongside, same era.
Multilayer convolutional sparse modeling: Pursuit and dictionary learning
Jeremias Sulam, Vardan Papyan, Yaniv Romano, and Michael Elad · 2018
Cited alongside, same era.

Then

Multi-layer sparse coding: the holistic way
Aviad Aberdam, Jeremias Sulam, and Michael Elad · 2019
Later among the works it cites.
Seeing what a gan cannot generate
David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, and Antonio Torralba · 2019
Later among the works it cites.
Convolutional analysis operator learning: acceleration and convergence
Il Yong Chun and Jeffrey A Fessler · 2019
Later among the works it cites.
Global guarantees for enforcing deep generative priors by empirical risk
Paul Hand and Vladislav Voroninski · 2019
Later among the works it cites.
Fast and provable admm for learning with generative priors
Fabian Latorre, Armin eftekhari, and Volkan Cevher · 2019
Later among the works it cites.
Inverting deep generative models, one layer at a time
Qi Lei, Ajil Jalal, Inderjit S Dhillon, and Alexandros G Dimakis · 2019
Later among the works it cites.
Adversarial noise attacks of deep learning architectures: Stability analysis via sparse-modeled signals
Yaniv Romano, Aviad Aberdam, Jeremias Sulam, and Michael Elad · 2019
Later among the works it cites.
On multi-layer basis pursuit, efficient algorithms and convolutional neural networks
Jeremias Sulam, Aviad Aberdam, Amir Beck, and Michael Elad · 2019
Later among the works it cites.
Barycenters of natural images constrained wasserstein barycenters for image morphing
Dror Simon and Aviad Aberdam · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…