Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks

Vertolli, Michael O.; Davies, Jim

doi:10.48550/arxiv.1708.02237

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adam optimizer was used with a learning rate of 0.00008, initial value of 𝑘 𝑡 as 0, 𝜆 𝑘 as 0.001, 𝛾 as 0.7, and minibatch size of 16 (see Section 5.1.2). The learning rate parameter is set with reference to the settings of previous papers that studied image quality by using BEGAN [48,49].…”

Section: Proposed Generative Modelsmentioning

confidence: 99%

Deep Generative Design: Integration of Topology Optimization and Generative Models

Jung

Kim

et al. 2019

Journal of Mechanical Design

270

124

View full text Add to dashboard Cite

Deep learning has recently been applied to various research areas of design optimization. This study presents the need and effectiveness of adopting deep learning for generative design (or design exploration) research area. This work proposes an artificial intelligent (AI)-based deep generative design framework that is capable of generating numerous design options which are not only aesthetic but also optimized for engineering performance. The proposed framework integrates topology optimization and generative models (e.g., generative adversarial networks (GANs)) in an iterative manner to explore new design options, thus generating a large number of designs starting from limited previous design data. In addition, anomaly detection can evaluate the novelty of generated designs, thus helping designers choose among design options. The 2D wheel design problem is applied as a case study for validation of the proposed framework. The framework manifests better aesthetics, diversity, and robustness of generated designs than previous generative design methods. Nomenclature: expectation : differentiable function of discriminator : differentiable function of generator : noise variable ℒ: loss function of autoencoder c: compliance : density variable ̃: filtered density variable ̃̅ : projected density variable : penalization factor Generative Models for Generative DesignGenerative models, one of the promising deep learning areas, can enhance research on generative design. The generative model is an algorithm for constructing a generator that learns the probability distribution of training data and generates new data based on learned probability distribution. In particular, variational autoencoder (VAE) and generative adversarial network (GAN) are popular generative models used in design optimization, where high-dimensional design variables are encoded in low-dimensional design space [13,14]. In addition, these models are utilized in the design exploration and shape parameterization [8,9].The use of generative model to produce engineering designs directly is limited [23]. However, this study claims that the limitations can be overcome by integrating with topology optimization. First, the generative model requires a number of training data, but accumulated training data for various designs in the industry are confidential and difficult to access. A number of designs obtained from topology optimization are expected to serve as training data. Second, the generative model cannot guarantee feasible engineering. In this case,

show abstract

Section: Proposed Generative Modelsmentioning

confidence: 99%

Deep Generative Design: Integration of Topology Optimization and Generative Models

Jung

Kim

et al. 2019

Journal of Mechanical Design

270

124

View full text Add to dashboard Cite

show abstract

“…The key moment from our point of view is selection of the reconstruction loss l(; ). Following the conclusions in [52] about this objective we have chosen two terms loss: L 1 distance for each channel in the RGB color space and gradient magnitude of Y channel in the YIQ color space:…”

Section: Reconstruction Lossmentioning

confidence: 99%

High Diversity Attribute Guided Face Generation with GANs

Izutov

2018

Preprint

View full text Add to dashboard Cite

In this work we focused on GAN-based solution for the attribute guided face synthesis. Previous works exploited GANs for generation of photo-realistic face images and did not pay attention to the question of diversity of the resulting images. The proposed solution in its turn introducing novel latent space of unit complex numbers is able to provide the diversity on the "birthday paradox" score 3 times higher than the size of the training dataset. It is important to emphasize that our result is shown on relatively small dataset (20k samples vs 200k) while preserving photo-realistic properties of generated faces on significantly higher resolution (128x128 in comparison to 32x32 of previous works).

show abstract

Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks

Cited by 2 publications

References 20 publications

Deep Generative Design: Integration of Topology Optimization and Generative Models

Deep Generative Design: Integration of Topology Optimization and Generative Models

High Diversity Attribute Guided Face Generation with GANs

Contact Info

Product

Resources

About