mlsanityData to 7 Oct 2026

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

arXiv 2103.05844 ↗First posted 10 Mar 2021cs.LG cs.DB stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

In this paper, we present "BIKED," a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: 1) Are there prominent gaps in the current bicycle market and design space? We explore the design space using unsupervised dimensionality reduction methods. 2) How does one identify the class of a bicycle and what factors play a key role in defining it? We address the bicycle classification task by training a multitude of classifiers using different forms of design data and identifying parameters of particular significance through permutation-based interpretability analysis. 3) How does one synthesize new bicycles using different representation methods? We consider numerous machine learning methods to generate new bicycle models as well as interpolate between and extrapolate from existing models using Variational Autoencoders. The dataset and code are available at http://decode.mit.edu/projects/biked/.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 8 of its 36 references that are in the map. First posted on arXiv 10 Mar 2021.

Builds on

8 of 36 references.

References · 8

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019An Introduction to Variational Autoencoderscited by 997
  5. 2019Modeling Tabular data using Conditional GANcited by 695
  6. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  7. 2017Neural networks for topology optimizationcited by 39
  8. 2019A deep Convolutional Neural Network for topology optimization with strong generalization abilitycited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 6; 2025: 6; 2026: 3.

27 papers.

Sort:

By area:

  1. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  2. 2022Diffusion Models Beat GANs on Topology Optimizationcited by 79
  3. 2023Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Designcited by 22
  4. 2023Ship-D: Ship Hull Dataset for Design Optimization using Machine Learningcited by 12
  5. 2022FRAMED: An AutoML Approach for Structural Performance Prediction of Bicycle Framescited by 11
  6. 2022Design Target Achievement Index: A Differentiable Metric to Enhance Deep Generative Models in Multi-Objective Inverse Designcited by 6
  7. 2023DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applicationscited by 6
  8. 2023On the Noise Scheduling for Generating Plausible Designs with Diffusion Modelscited by 6
  9. 2025EngiBench: A Framework for Data-Driven Engineering Design Researchcited by 6
  10. 2023MCD: A Model-Agnostic Counterfactual Search Method For Multi-modal Design Modificationscited by 5
  11. 2025BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraintscited by 5
  12. 2022Towards Goal, Feasibility, and Diversity-Oriented Deep Generative Models in Designcited by 3
15 more
  1. 2024Fr'echet Denoised Distance: Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencodercited by 3
  2. 2024Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conceptioncited by 3
  3. 2024BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designscited by 2
  4. 2025Multi-Component VAE with Gaussian Markov Random Fieldcited by 2
  5. 2023Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identificationcited by 1
  6. 2024Bridging Design Gaps: A Parametric Data Completion Approach With Graph Guided Diffusion Modelscited by 1
  7. 20243DArticCyclists: Generating Synthetic Articulated 8D Pose-Controllable Cyclist Data for Computer Vision Applicationscited by 1
  8. 2024Data Publishing in Mechanics and Dynamics: Challenges, Guidelines, and Examples from Engineering Designcited by 1
  9. 2023A Meta-Generation framework for Industrial System Generationcited by 0
  10. 2025Masked Conditioning for Deep Generative Modelscited by 0
  11. 2025Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI Eracited by 0
  12. 2025Flow Battery Manifold Design with Heterogeneous Inputs Through Generative Adversarial Neural Networkscited by 0
  13. 2026DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentationcited by 0
  14. 2026PhysicsBench: A Unified Leaderboard for Generative and Predictive Models in Engineering Design and Simulationcited by 0
  15. 2026MiDShip: Multimodal Dataset of Ship Cargo Hold Structures for Engineering Designcited by 0