paper-with-me

홈 › Papers

Concept Activation Vectors for Generating User-Defined 3D Shapes

2022-04-29 · Stefan Druc, Aditya Balu, Peter Wooldridge, Adarsh Krishnamurthy, Soumik Sarkar

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.

📄 PDF Abstract BibTeX arXiv:2205.02102

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays

2025-06-04 · Bulat Maksudov, Kathleen Curran, Alessandra Mileo

An essential step in deploying medical imaging models is ensuring alignment with clinical knowledge and interpretability. We focus on mapping clinical concepts into the latent space of generative models to identify Conce…

Clinical Knowledge

Knowledge graphs for empirical concept retrieval

2024-04-10 · Lenka Tětková, Teresa Karen Scheidt, Maria Mandrup Fogh, Ellen Marie Gaunby Jørgensen 외

Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based exp…

General KnowledgeKnowledge GraphsRetrieval

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

2017-11-30 · ICML 2018 7 · Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai 외

The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than hi…

General Classificationimage-classificationImage Classification

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability

2025-08-28 · Zhenghao He, Sanchit Sinha, Guangzhi Xiong, Aidong Zhang arxiv

Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when computed independently at different layers, CA…

Contrastive Learning

On The Variability of Concept Activation Vectors

2025-09-28 · Julia Wenkmann, Damien Garreau arxiv

One of the most pressing challenges in artificial intelligence is to make models more transparent to their users. Recently, explainable artificial intelligence has come up with numerous method to tackle this challenge. A…

Feature Importance