3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in design-synthesis-10
No benchmarks available.
Use these libraries to find design-synthesis-10 models and implementations
No datasets available.
No subtasks available.
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.
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.
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.
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.
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.
Adding a benchmark result helps the community track progress.