Related papers: Locality-aware Concept Bottleneck Model

With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but they are generally…

We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models. At the core of SCBMs lies the assumption that causal effects between high-dimensional variables only depend on low-dimensional summary…

We revisit language bottleneck models as an approach to ensuring the explainability of deep learning models for image classification. Because of inevitable information loss incurred in the step of converting images into language, the…

Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions. A key property of CBMs is that they support…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a…

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critical for model…

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' nature poses challenges for responsible implementation. Although…

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Material classification has emerged as a critical task in computer vision and graphics, supporting the assignment of accurate material properties to a wide range of digital and real-world applications. While traditionally framed as an image…

We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market's high-dimensional information…

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…

In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-language models (VLMs), despite achieving significant progress…

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts…

Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like…

Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label consistency. When a dataset contains concept-level inconsistencies, identical concept…

Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model…

Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization…