mlsanityData to 7 Oct 2026

Concept Activation Vectors for Generating User-Defined 3D Shapes

arXiv 2205.02102 ↗First posted 29 Apr 2022cs.CV cs.GR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD). The field of parametric CAD can be limited by the difficulty of expressing high-level design concepts in terms of a few numeric parameters. In this paper, we use a deep learning architectures to encode high dimensional 3D shapes into a vectorized latent representation that can be used to describe arbitrary concepts. Specifically, we train a simple auto-encoder to parameterize a dataset of complex shapes. To understand the latent encoded space, we use the idea of Concept Activation Vectors (CAV) to reinterpret the latent space in terms of user-defined concepts. This allows modification of a reference design to exhibit more or fewer characteristics of a chosen concept or group of concepts. We also test the statistical significance of the identified concepts and determine the sensitivity of a physical quantity of interest across the dataset.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

34 of 47 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  10. 2018Sanity Checks for Saliency Mapscited by 1,149
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 707
22 more
  1. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  2. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  3. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  4. 2016Adversarial Feature Learningcited by 350
  5. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  6. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  7. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  8. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 197
  9. 2019CvxNet: Learnable Convex Decompositioncited by 173
  10. 2020Debugging Tests for Model Explanationscited by 146
  11. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  12. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  13. 2019Sanity Checks for Saliency Metricscited by 119
  14. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  15. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  16. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  17. 2017Learning Representations and Generative Models for 3D Point Cloudscited by 21
  18. 2021Surrogate Model-Based Explainability Methods for Point Cloud NNscited by 18
  19. 2020Explainable Artificial Intelligence for Manufacturing Cost Estimation and Machining Feature Visualizationcited by 15
  20. 2018P2P-NET: Bidirectional Point Displacement Net for Shape Transformcited by 11
  21. 2019Virtual Thin Slice: 3D Conditional GAN-based Super-resolution for CT Slice Intervalcited by 11
  22. 20163D Keypoint Detection Based on Deep Neural Network with Sparse Autoencodercited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024LG-CAV: Train Any Concept Activation Vector with Language Guidancecited by 9
  2. 2025EVolutionary Independent DEtermiNistiC Explanationcited by 0