mlsanityData to 7 Oct 2026

SELTO: Sample-Efficient Learned Topology Optimization

arXiv 2209.05098 ↗First posted 12 Sep 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent developments in Deep Learning (DL) suggest a vast potential for Topology Optimization (TO). However, while there are some promising attempts, the subfield still lacks a firm footing regarding basic methods and datasets. We aim to address both points. First, we explore physics-based preprocessing and equivariant networks to create sample-efficient components for TO DL pipelines. We evaluate them in a large-scale ablation study using end-to-end supervised training. The results demonstrate a drastic improvement in sample efficiency and the predictions' physical correctness. Second, to improve comparability and future progress, we publish the two first TO datasets containing problems and corresponding ground truth solutions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 59 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

27 of 59 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  5. 2016Group Equivariant Convolutional Networkscited by 1,154
  6. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  7. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  8. 2017Road Extraction by Deep Residual U-Netcited by 333
  9. 2021NeRV: Neural Representations for Videoscited by 255
  10. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 193
  11. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  12. 2017Generalization in Deep Learningcited by 146
15 more
  1. 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
  2. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 96
  3. 2018Flexible Neural Representation for Physics Predictioncited by 91
  4. 2020TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domaincited by 65
  5. 2021Geometric Deep Learning and Equivariant Neural Networkscited by 64
  6. 2019Neural reparameterization improves structural optimizationcited by 44
  7. 2021NTopo: Mesh-free Topology Optimization using Implicit Neural Representationscited by 41
  8. 2018Deep learning for determining a near-optimal topological design without any iterationcited by 40
  9. 2017Neural networks for topology optimizationcited by 39
  10. 20183D Topology Optimization using Convolutional Neural Networkscited by 27
  11. 2019A Novel Topology Optimization Approach using Conditional Deep Learningcited by 17
  12. 2019A deep Convolutional Neural Network for topology optimization with strong generalization abilitycited by 16
  13. 2020Segmentation Loss Odysseycited by 7
  14. 2018Robustness of Rotation-Equivariant Networks to Adversarial Perturbationscited by 6
  15. 2019A New CGAN Technique for Constrained Topology Design Optimizationcited by 5

Built on by

Not cited yet.