Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning

• URL: http://arxiv.org/abs/2503.13429v2
• Date: Mon, 29 Sep 2025 10:24:06 GMT
• Title: Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
• Authors: Nhi Pham, Artur Jesslen, Bernt Schiele, Adam Kortylewski, Jonas Fischer,
• Abstract summary: CAVE - Concept Aware Volumes for Explanations - is a new direction that unifies interpretability and robustness in image classification.<n>We propose 3D Consistency (3D-C), a metric to measure spatial consistency of concepts.<n>CAVE achieves competitive classification performance while discovering consistent and meaningful concepts across images in various OOD settings.
• Score: 68.3379650993108
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning [46.85417907244265]
  We propose an interpretable single-view 3DGS framework, termed 3DisGS, to discover both coarse- and fine-grained 3D semantics. Our model achieves 3D disentanglement while preserving high-quality and rapid reconstruction.
  arXiv  Detail & Related papers  (2025-04-05T14:42:13Z)
• Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding [58.38294408121273]
  We propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D. Our method addresses two key challenges: (1) incorporating semantic priors from VLMs alongside the geometric knowledge of spatially-aware vision foundation models, and (2) using a novel deterministic uncertainty estimation to capture model-specific uncertainties.
  arXiv  Detail & Related papers  (2025-03-20T20:58:48Z)
• MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image [8.095737075287204]
  We propose a novel single-image 3D reconstruction method called Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (MESC-3D)<n>Specifically, we design an Effective Semantic Mining Module to establish connections between point clouds and image semantic attributes.<n>This module incorporates semantic understanding of spatial structures, enabling the model to interpret and reconstruct 3D objects with greater accuracy and realism.
  arXiv  Detail & Related papers  (2025-02-28T09:02:15Z)
• ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers [29.932706137805713]
  ASCENT-ViT is an attention-based, concept learning framework for Vision Transformers (ViTs)<n>It composes scale and position-aware representations from multiscale feature pyramids and ViT patch representations, respectively.<n>It can be utilized as a classification head on top of standard ViT backbones for improved predictive performance and accurate and robust concept explanations.
  arXiv  Detail & Related papers  (2025-01-16T00:45:05Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning [10.51523800391153]
  We evaluate and enhance the 3D awareness of ViT-based models.<n>We propose a simple yet effective finetuning strategy based on 3D correspondences.
  arXiv  Detail & Related papers  (2024-11-29T04:02:11Z)
• SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection [19.75965521357068]
  We propose a novel approach called SOGDet (Semantic-Occupancy Guided Multi-view 3D Object Detection) to improve the accuracy of 3D object detection. Our results show that SOGDet consistently enhance the performance of three baseline methods in terms of nuScenes Detection Score (NDS) and mean Average Precision (mAP) This indicates that the combination of 3D object detection and 3D semantic occupancy leads to a more comprehensive perception of the 3D environment, thereby aiding build more robust autonomous driving systems.
  arXiv  Detail & Related papers  (2023-08-26T07:38:21Z)
• Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding [58.924180772480504]
  3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. We propose to leverage weakly supervised annotations to learn the 3D visual grounding model. We design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2023-07-18T13:49:49Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• Renderers are Good Zero-Shot Representation Learners: Exploring Diffusion Latents for Metric Learning [1.0152838128195467]
  We use retrieval as a proxy for measuring the metric learning properties of the latent spaces of Shap-E. We find that Shap-E representations outperform those of the classical EfficientNet baseline representations zero-shot. These findings give preliminary indication that 3D-based rendering and generative models can yield useful representations for discriminative tasks in our innately 3D-native world.
  arXiv  Detail & Related papers  (2023-06-19T06:41:44Z)
• NOVUM: Neural Object Volumes for Robust Object Classification [22.411611823528272]
  We show that explicitly integrating 3D compositional object representations into deep networks for image classification leads to a largely enhanced generalization in out-of-distribution scenarios. In particular, we introduce a novel architecture, referred to as NOVUM, that consists of a feature extractor and a neural object volume for every target object class. Our experiments show that NOVUM offers intriguing advantages over standard architectures due to the 3D compositional structure of the object representation.
  arXiv  Detail & Related papers  (2023-05-24T03:20:09Z)
• Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach [53.376029341079054]
  We propose a combined generative and contrastive neural architecture for learning latent representations of 3D shapes.<n>The architecture uses two encoder branches for voxel grids and multi-view images from the same underlying shape.
  arXiv  Detail & Related papers  (2023-01-11T18:14:24Z)
• CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection [57.44434974289945]
  We propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework. Our framework takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene. In addition to 3D object detection, we investigate the effectiveness of our framework for the problem of 3D object counting.
  arXiv  Detail & Related papers  (2022-09-13T05:26:09Z)
• Understanding Robust Learning through the Lens of Representation Similarities [37.66877172364004]
  robustness to adversarial examples has emerged as a desirable property for deep neural networks (DNNs) In this paper, we aim to understand how the properties of representations learned by robust training differ from those obtained from standard, non-robust training.
  arXiv  Detail & Related papers  (2022-06-20T16:06:20Z)
• Spatial-temporal Concept based Explanation of 3D ConvNets [5.461115214431218]
  We present a 3D ACE (Automatic Concept-based Explanation) framework for interpreting 3D ConvNets. In our approach, videos are represented using high-level supervoxels, which is straightforward for human to understand. Experiments show that our method can discover spatial-temporal concepts of different importance-levels.
  arXiv  Detail & Related papers  (2022-06-09T08:04:46Z)
• Stereo Object Matching Network [78.35697025102334]
  This paper presents a stereo object matching method that exploits both 2D contextual information from images and 3D object-level information. We present two novel strategies to handle 3D objectness in the cost volume space: selective sampling (RoISelect) and 2D-3D fusion.
  arXiv  Detail & Related papers  (2021-03-23T12:54:43Z)
• Learning to Reconstruct and Segment 3D Objects [4.709764624933227]
  We aim to understand scenes and the objects within them by learning general and robust representations using deep neural networks. This thesis makes three core contributions from object-level 3D shape estimation from single or multiple views to scene-level semantic understanding.
  arXiv  Detail & Related papers  (2020-10-19T15:09:04Z)
• Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection [102.62963605429508]
  Point cloud semantic segmentation plays an essential role in autonomous driving. Current 3D semantic segmentation networks focus on convolutional architectures that perform great for well represented classes. We propose a novel Aware 3D Semantic Detection (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task.
  arXiv  Detail & Related papers  (2020-09-22T14:17:40Z)
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
  We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
  arXiv  Detail & Related papers  (2019-12-26T08:48:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.