SCENE-Net V2: Interpretable Multiclass 3D Scene Understanding with Geometric Priors

Diogo Mateus Lavado, Claudia Soares, Alessandra Micheletti

Track: Proceedings

Keywords: 3D Semantic Segmentation, Group Equivariant Non-Expansive Operators, Explainable Machine Learning

TL;DR: We introduce SCENE-Net V2, an interpretable model for 3D scene understanding using GENEOs to incorporate geometric priors. We advocate for GENEO-based architectures as transparent feature extraction tools for 3D scene benchmarks.

Abstract:

In this paper, we present SCENE-Net V2, a new resource-efficient, \textbf{gray-box model} for multiclass 3D scene understanding. SCENE-Net V2 leverages Group Equivariant Non-Expansive Operators (GENEOs) to incorporate fundamental geometric priors as inductive biases, offering a more transparent alternative to the prevalent black-box models in the domain.
This model addresses the limitations of its white-box predecessor, SCENE-Net, by expanding its applicability from pole-like structures to a wider range of datasets with detailed 3D elements.
Our model achieves the sweet-spot between application and transparency: SCENE-Net V2 is a general method for object identification with interpretability guarantees.
Our experimental results demonstrate that SCENE-Net V2 achieves competitive performance with a significantly lower parameter count. Furthermore, we propose the use of GENEO-based architectures as a feature extraction tool for black-box models, enabling an increase in performance by adding a minimal number of meaningful parameters.
Our code is available in: https://github.com/dlavado/SCENE-Net-V2

Submission Number: 44