# Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning

arXiv: https://arxiv.org/abs/2503.13429 · HTML: https://mlsanity.com/paper/2503.13429/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 30 of 35)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors](https://mlsanity.com/paper/2006.15417/) (2020)
- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [Robust Object Detection under Occlusion with Context-Aware CompositionalNets](https://mlsanity.com/paper/2005.11643/) (2020)
- [Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees](https://mlsanity.com/paper/2301.11911/) (2023)
- [Sparse Modeling for Image and Vision Processing](https://mlsanity.com/paper/1411.3230/) (2014)
- [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2111.14341/) (2021)
- [Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models](https://mlsanity.com/paper/2412.18605/) (2024)
- [Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis](https://mlsanity.com/paper/2202.07728/) (2022)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [Fast Axiomatic Attribution for Neural Networks](https://mlsanity.com/paper/2111.07668/) (2021)
- [ImageNet3D: Towards General-Purpose Object-Level 3D Understanding](https://mlsanity.com/paper/2406.09613/) (2024)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [On the Concept Trustworthiness in Concept Bottleneck Models](https://mlsanity.com/paper/2403.14349/) (2024)
- [Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation](https://mlsanity.com/paper/2402.18919/) (2024)

## Built on by (most cited first, 2 of 2)

- [Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance](https://mlsanity.com/paper/2605.31304/) (2026)
- [3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling](https://mlsanity.com/paper/2606.11446/) (2026)

## Abstract (arXiv)

With the rise of deep neural networks, especially in safety-critical applications, robustness and interpretability are crucial to ensure their trustworthiness. Recent advances in 3D-aware classifiers that map image features to volumetric representation of objects, rather than relying solely on 2D appearance, have greatly improved robustness on out-of-distribution (OOD) data. Such classifiers have not yet been studied from the perspective of interpretability. Meanwhile, current concept-based XAI methods often neglect OOD robustness. We aim to address both aspects with CAVE - Concept Aware Volumes for Explanations - a new direction that unifies interpretability and robustness in image classification. We design CAVE as a robust and inherently interpretable classifier that learns sparse concepts from 3D object representation. We further propose 3D Consistency (3D-C), a metric to measure spatial consistency of concepts. Unlike existing metrics that rely on human-annotated parts on images, 3D-C leverages ground-truth object meshes as a common surface to project and compare explanations across concept-based methods. CAVE achieves competitive classification performance while discovering consistent and meaningful concepts across images in various OOD settings. Code available at https://github.com/phamleyennhi/CAVE.