adversarial-10

Design Synthesis

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in design-synthesis-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find design-synthesis-10 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

PaDGAN: A Generative Adversarial Network for Performance Augmented Diverse Designs

Faez Ahmed, Wei Chen•Tue Feb 25 2020

A new Determinantal Point Processes based loss function for probabilistic modeling of diversity and quality is proposed and developed, named “Performance Augmented Diverse Generative Adversarial Network” or PaDGAN, which can generate novel high-quality designs with good coverage of the design space.

12

Content

0

Paper Graph

CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis

Faez Ahmed, A. Nobari, Muhammad Fathy Rashad•Tue Mar 09 2021

An automated method, named CreativeGAN, is proposed that can create new bicycle designs with unique frames and handles, and generalize rare novelties to a broad set of designs, and demonstrates a way to rethink creative design synthesis and exploration.

56 0

Paper Graph

Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis

Faez Ahmed, A. Nobari, Wei Chen•Tue Mar 09 2021

A conditional deep generative model, Range-GAN, is proposed to achieve automatic design synthesis subject to range constraints and addresses the sparse conditioning issue in data-driven inverse design problems by introducing a label-aware self-augmentation approach.

16 0

Paper Graph

BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks

Lyle Regenwetter, Brent Curry, Faez Ahmed•Tue Mar 09 2021

This paper discusses the processing of the dataset, then highlights some prominent research questions that BIKED can help address and applies unsupervised embedding methods to study the design space and identifies key takeaways from this analysis.

44 0

Paper Graph

PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design

Faez Ahmed, A. Nobari, Wei Chen•Sun Jun 06 2021

A new model, named Performance Conditioned Diverse Generative Adversarial Network (PcDGAN), is proposed, which introduces a singular vicinal loss combined with a Determinantal Point Processes (DPP) based loss function to enhance diversity and outperforms state-of-the-art GAN models.

59 0

Paper Graph

Adding a benchmark result helps the community track progress.