paper-with-me

홈 › Papers

Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

2018-07-19 · ICLR 2019 5 · David Berthelot, Colin Raffel, Aurko Roy, Ian Goodfellow

Autoencoders provide a powerful framework for learning compressed representations by encoding all of the information needed to reconstruct a data point in a latent code. In some cases, autoencoders can "interpolate": By decoding the convex combination of the latent codes for two datapoints, the autoencoder can produce an output which semantically mixes characteristics from the datapoints. In this paper, we propose a regularization procedure which encourages interpolated outputs to appear more realistic by fooling a critic network which has been trained to recover the mixing coefficient from interpolated data. We then develop a simple benchmark task where we can quantitatively measure the extent to which various autoencoders can interpolate and show that our regularizer dramatically improves interpolation in this setting. We also demonstrate empirically that our regularizer produces latent codes which are more effective on downstream tasks, suggesting a possible link between interpolation abilities and learning useful representations.

📄 PDF Abstract BibTeX arXiv:1807.07543

Code (7)

anonymous-iclr-2019/acai-iclr-2019 공식 구현 tf
brain-research/acai 공식 구현 tf
baohq1595/aae-experiment tf
dariocazzani/pytorch-ae pytorch
greentfrapp/acai-berry tf
ivanvovk/controllable-face-generation pytorch
sidwa/ae_thesis pytorch

Similar Papers 제목 키워드 기반

Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation

2021-02-23 · Xiaoyang Qu, Jianzong Wang, Jing Xiao

Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which mi…

Knowledge Distillation

Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey

2021-11-26 · Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

This is a tutorial and survey paper on Generative Adversarial Network (GAN), adversarial autoencoders, and their variants. We start with explaining adversarial learning and the vanilla GAN. Then, we explain the condition…

Dimensionality ReductionFace GenerationGenerative Adversarial NetworkImage Generation+4

Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders

2020-01-15 · Andrea Valenti, Antonio Carta, Davide Bacciu

We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbu…

Music Modeling

Disentangling Autoencoders (DAE)

2022-02-20 · Jaehoon Cha, Jeyan Thiyagalingam

Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations in group-theor…

Disentanglement

Understanding Adversarial Attacks on Autoencoders

2021-01-01 · Elsa Riachi, Frank Rudzicz

Adversarial vulnerability is a fundamental limitation of deep neural networks which remains poorly understood. Recent work suggests that adversarial attacks on deep neural network classifiers exploit the …

Compressive SensingKnowledge Distillation