Object Centric Concept Bottlenecks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Steinmann, David, Stammer, Wolfgang, Wüst, Antonia, Kersting, Kristian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916992253952000
author Steinmann, David
Stammer, Wolfgang
Wüst, Antonia
Kersting, Kristian
author_facet Steinmann, David
Stammer, Wolfgang
Wüst, Antonia
Kersting, Kristian
contents Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding) and then applying a linear classifier on the resulting concept activations, enabling transparent decision-making. However, their reliance on holistic image encodings limits their expressiveness in object-centric real-world settings and thus hinders their ability to solve complex vision tasks beyond single-label classification. To tackle these challenges, we introduce Object-Centric Concept Bottlenecks (OCB), a framework that combines the strengths of CBMs and pre-trained object-centric foundation models, boosting performance and interpretability. We evaluate OCB on complex image datasets and conduct a comprehensive ablation study to analyze key components of the framework, such as strategies for aggregating object-concept encodings. The results show that OCB outperforms traditional CBMs and allows one to make interpretable decisions for complex visual tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Object Centric Concept Bottlenecks
Steinmann, David
Stammer, Wolfgang
Wüst, Antonia
Kersting, Kristian
Machine Learning
Artificial Intelligence
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding) and then applying a linear classifier on the resulting concept activations, enabling transparent decision-making. However, their reliance on holistic image encodings limits their expressiveness in object-centric real-world settings and thus hinders their ability to solve complex vision tasks beyond single-label classification. To tackle these challenges, we introduce Object-Centric Concept Bottlenecks (OCB), a framework that combines the strengths of CBMs and pre-trained object-centric foundation models, boosting performance and interpretability. We evaluate OCB on complex image datasets and conduct a comprehensive ablation study to analyze key components of the framework, such as strategies for aggregating object-concept encodings. The results show that OCB outperforms traditional CBMs and allows one to make interpretable decisions for complex visual tasks.
title Object Centric Concept Bottlenecks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.24492