arXiv AI
Jun 30
On the Faithfulness of Post-Hoc Concept Bottleneck Models
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
Auditing Where Concept Bottleneck Accuracy Comes From on CUB
Related stories
arXiv Machine Learning
Jun 16
Assessing Reliability of Symbol Detection in Concept Bottleneck Models
arXiv:2606. 16535v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols.
arXiv Machine Learning
Jun 4
Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention
arXiv:2606. 04364v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable.
arXiv Computer Vision
Sep 17
How to make effective use of domain experts for image classification?
arXiv:2609.17749v1 Announce Type: new Abstract: A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explo...
arXiv Machine Learning
Aug 12
Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv Computer Vision
Oct 1
Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing
arXiv:2609.38603v1 Announce Type: new Abstract: While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability...
arXiv AI
Oct 1
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remai...
arXiv Machine Learning
Aug 12
Concept Labels Are Not Enough: Rethinking Concept Bottleneck Models through Representation Integrity
arXiv:2510. 15770v4 Announce Type: replace-cross Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control.
arXiv AI
Oct 7
AnyBottle: A Recipe to Only Keep the Concepts You Really Need
arXiv:2610.08552v1 Announce Type: new Abstract: Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally req...
arXiv Computer Vision
Oct 15
Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
arXiv:2605.20337v2 Announce Type: replace Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks in...
arXiv AI
Oct 15
Explainable Visual Anomaly Detection via Concept Bottleneck Models
The paper introduces Concept-Aware Visual Anomaly Detection (Concept-Aware VAD), a framework that extends Concept Bottleneck Models to visual anomaly detection. It offers dual-branch architecture: a concept branch for human-interpretable descriptions and a visual branch for pixel-level localization, evaluated on three VAD benchmarks with competitive performance. A user study shows higher effectiveness and lower misleading rates compared to state-of-the-art explainers, and concept-level interventions improve unsupervised detection.
arXiv AI
Jun 30
Can Machines Really See Objects in Images? A Study Based on Syntactic Distance and Visual Self-Referential Instances
arXiv:2606. 29416v1 Announce Type: cross Abstract: Can a vision model truly see an object, or does it only fit surface-level visual cues?