Hoeffding Concept Bottleneck Models with Applications to Overhead Images
Summary
Introduces Hoeffding Concept Bottleneck Models (HCBM), a nonlinear and sparse aggregation of concept scores using Hoeffding functional decomposition of gradient-boosted trees, for improved explainability and accuracy in classification and object detection tasks, with applications to overhead images.
View Cached Full Text
Cached at: 06/02/26, 03:39 PM
# Hoeffding Concept Bottleneck Models with Applications to Overhead Images Source: [https://arxiv.org/abs/2606.00082](https://arxiv.org/abs/2606.00082) [View PDF](https://arxiv.org/pdf/2606.00082) > Abstract:Explainability of deep learning algorithms is critical for computer\-vision applications with high\-stake decisions\. Concept bottleneck models \(CBM\) have recently shown promising performance to provide explainable and accurate predictions for classification problems, based on a bottleneck of high\-level concepts\. Existing CBM methods rely on a linear aggregation of the concept scores to compute predictions\. However, a large number of concepts is often used in this linear approach, which undermines explainability and favors information leakage\. In general, the underlying relation between concepts and output logits is not linear\. Therefore, we introduce Hoeffding Concept Bottleneck Models \(HCBM\), which build on the Hoeffding functional decomposition of gradient\-boosted trees to provide non\-linear and sparse aggregations of concept scores, and generate compact predictions using prime implicants\. HCBM are proved to be robust to interconcept leakage, and outperform standard linear CBM in practice, as shown in extensive experiments\. Beyond classification, HCBM can be adapted to object detection, and we focus on a challenging case with overhead images to show the high performance of HCBM in these settings\. ## Submission history From: Clement Benard \[[view email](https://arxiv.org/show-email/91d74caa/2606.00082)\] \[via CCSD proxy\] **\[v1\]**Fri, 22 May 2026 14:00:30 UTC \(3,125 KB\)
Similar Articles
Towards Fine-Grained and Verifiable Concept Bottleneck Models
This paper proposes a fine-grained concept bottleneck model framework that grounds each concept in localized visual evidence, enabling direct verification of concept correctness and improving transparency in medical imaging tasks.
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models
ReCBM proposes an uncertainty-gated relational reasoning framework for Concept Bottleneck Models, introducing concept relations like co-occurrence, implication, and exclusion to recover unreliable or missing concept states and improve interpretability and downstream predictions.
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
OceanCBM is a concept bottleneck model for spatiotemporal prediction and mechanistic interpretability in ocean forecasting, using mixed supervision to predict mixed layer heat content while imposing soft physical structure. The model achieves interpretable, physically grounded representations without sacrificing predictive skill.
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
This paper introduces HMH, a hierarchical multi-scale Graph Neural Network framework designed to address oversmoothing and oversquashing in heterophilous graphs. It utilizes spectral filters with Haar bases to achieve scalable learning and improved performance on node and graph classification tasks.
CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models
This paper proposes CLIF, a method using influence functions to interpret NLP models at both sample and concept levels within Concept Bottleneck Models, enabling transparent debugging and concept-level analysis.