mlsanityData to 7 Oct 2026

DEBOSH: Deep Bayesian Shape Optimization

arXiv 2109.13337 ↗First posted 28 Sep 2021cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) can predict the performance of an industrial design quickly and accurately and be used to optimize its shape effectively. However, to fully explore the shape space, one must often consider shapes deviating significantly from the training set. For these, GNN predictions become unreliable, something that is often ignored. For optimization techniques relying on Gaussian Processes, Bayesian Optimization (BO) addresses this issue by exploiting their ability to assess their own accuracy. Unfortunately, this is harder to do when using neural networks because standard approaches to estimating their uncertainty can entail high computational loads and reduced model accuracy. Hence, we propose a novel uncertainty-based method tailored to shape optimization. It enables effective BO and increases the quality of the resulting shapes beyond that of state-of-the-art approaches.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 33 of its 77 references that are in the map. First posted on arXiv 28 Sep 2021.

Builds on

33 of 77 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  12. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
21 more
  1. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  3. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  4. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  5. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  6. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  7. 2016Accelerating Eulerian Fluid Simulation With Convolutional Networkscited by 128
  8. 2018Deep Fluids: A Generative Network for Parameterized Fluid Simulationscited by 121
  9. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  10. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  11. 2020Masksembles for Uncertainty Estimationcited by 88
  12. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  13. 2017On weight initialization in deep neural networkscited by 67
  14. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  15. 2017Improving the Expected Improvement Algorithmcited by 54
  16. 2018Geodesic Convolutional Shape Optimizationcited by 37
  17. 2021Leveraging Self-Supervision for Cross-Domain Crowd Countingcited by 24
  18. 2021DeepMesh: Differentiable Iso-Surface Extractioncited by 14
  19. 2018Single-Model Uncertainties for Deep Learningcited by 6
  20. 2018Double Refinement Network for Efficient Indoor Monocular Depth Estimationcited by 5
  21. 2015Large scale three-dimensional topology optimisation of heat sinks cooled by natural convectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 2; 2025: 2; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 293
  2. 2023Swarm Reinforcement Learning For Adaptive Mesh Refinementcited by 16
  3. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  4. 2023Grounding Graph Network Simulators using Physical Sensor Observationscited by 15
  5. 2023Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderingscited by 15
  6. 2023Drag-guided diffusion models for vehicle image generationcited by 13
  7. 2024IT3: Idempotent Test-Time Trainingcited by 6
  8. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  9. 2022PartAL: Efficient Partial Active Learning in Multi-Task Visual Settingscited by 3
  10. 20253DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimizationcited by 3
  11. 2022Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping processcited by 1
  12. 2025Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learningcited by 1
2 more
  1. 2023Latent Task-Specific Graph Network Simulatorscited by 0
  2. 2026Example-driven Parametrisations for Bayesian Shape Optimisationcited by 0