paper-with-me

홈 › Papers

Inverting The Generator Of A Generative Adversarial Network (II)

2018-02-15 · Antonia Creswell, Anil A. Bharath

Generative adversarial networks (GANs) learn a deep generative model that is able to synthesise novel, high-dimensional data samples. New data samples are synthesised by passing latent samples, drawn from a chosen prior distribution, through the generative model. Once trained, the latent space exhibits interesting properties, that may be useful for down stream tasks such as classification or retrieval. Unfortunately, GANs do not offer an "inverse model", a mapping from data space back to latent space, making it difficult to infer a latent representation for a given data sample. In this paper, we introduce a technique, inversion, to project data samples, specifically images, to the latent space using a pre-trained GAN. Using our proposed inversion technique, we are able to identify which attributes of a dataset a trained GAN is able to model and quantify GAN performance, based on a reconstruction loss. We demonstrate how our proposed inversion technique may be used to quantitatively compare performance of various GAN models trained on three image datasets. We provide code for all of our experiments, https://github.com/ToniCreswell/InvertingGAN.

📄 PDF Abstract BibTeX arXiv:1802.05701

Code (1)

ToniCreswell/InvertingGAN 공식 구현 pytorch

Tasks

Generative Adversarial NetworkRetrieval

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Generative networks as inverse problems with Scattering transforms

2018-05-17 · ICLR 2018 1 · Tomás Angles, Stéphane Mallat

Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutiona…

Exploiting the Hidden Tasks of GANs: Making Implicit Subproblems Explicit

2021-01-28 · Romann M. Weber

We present an alternative perspective on the training of generative adversarial networks (GANs), showing that the training step for a GAN generator decomposes into two implicit subproblems. In the first, the discriminato…

regression

Source Generator Attribution via Inversion

2019-05-06 · Michael Albright, Scott McCloskey

With advances in Generative Adversarial Networks (GANs) leading to dramatically-improved synthetic images and video, there is an increased need for algorithms which extend traditional forensics to this new category of im…

SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks

2018-04-02 · Wen-Cheng Chen, Chien-Wen Chen, Min-Chun Hu

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most…

Generative Adversarial Network

Adversarial defenses via a mixture of generators

2021-10-05 · Maciej Żelaszczyk, Jacek Mańdziuk

In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial …

Adversarial Attack