Hoeffding Concept Bottleneck Models with Applications to Overhead Images

arXiv:2606.00082 · cs.LG, cs.AI, stat.ML · Submitted 2026-05-22 · Read on arXiv

cs.LG, cs.AI, stat.ML

Submitted: 2026-05-22

Updated: 2026-10-12

Code: https://github.com/ericenouen/cbdebug

Terminology

• Aggregation — 2× in this paper · explained in 1 episode
• Explainability — 2× in this paper · explained in 3 episodes
• Hoeffding Concept Bottleneck Models — 2× in this paper
• Information Leakage — 1× in this paper · explained in 2 episodes

Sources

• xView: Objects in Context in Overhead Imagery
• RTMDet: An Empirical Study of Designing Real-Time Object Detectors
• InterpretML: A Unified Framework for Machine Learning Interpretability
• Leakage and Interpretability in Concept-Based Models
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks