Concept bottleneck models
We seek to learn models that we can interact with using high-level concepts: if the model did
not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the …
not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the …
Learning bottleneck concepts in image classification
Interpreting and explaining the behavior of deep neural networks is critical for many tasks.
Explainable AI provides a way to address this challenge, mostly by providing per-pixel …
Explainable AI provides a way to address this challenge, mostly by providing per-pixel …
Promises and pitfalls of black-box concept learning models
Machine learning models that incorporate concept learning as an intermediate step in their
decision making process can match the performance of black-box predictive models while …
decision making process can match the performance of black-box predictive models while …
Static and dynamic concepts for self-supervised video representation learning
In this paper, we propose a novel learning scheme for self-supervised video representation
learning. Motivated by how humans understand videos, we propose to first learn general …
learning. Motivated by how humans understand videos, we propose to first learn general …
Semantically Interpretable Activation Maps: what-where-how explanations within CNNs
A main issue preventing the use of Convolutional Neural Networks (CNN) in end user
applications is the low level of transparency in the decision process. Previous work on CNN …
applications is the low level of transparency in the decision process. Previous work on CNN …
[HTML][HTML] Semantic bottlenecks: Quantifying and improving inspectability of deep representations
Today's deep learning systems deliver high performance based on end-to-end training but
are notoriously hard to inspect. We argue that there are at least two reasons making …
are notoriously hard to inspect. We argue that there are at least two reasons making …
Salad: Self-assessment learning for action detection
G Vaudaux-Ruth… - Proceedings of the …, 2021 - openaccess.thecvf.com
Literature on self-assessment in machine learning mainly focuses on the production of well-
calibrated algorithms through consensus frameworks ie calibration is seen as a problem …
calibrated algorithms through consensus frameworks ie calibration is seen as a problem …
A novel intrinsically explainable model with semantic manifolds established via transformed priors
G Shi, M Yang, D Gao - Knowledge-Based Systems, 2022 - Elsevier
Because humans instinctively trust and interact with explainable representations instead of
latent features, intrinsically interpretable models (IIMs) aimed at representations with …
latent features, intrinsically interpretable models (IIMs) aimed at representations with …
Automated Molecular Concept Generation and Labeling with Large Language Models
Artificial intelligence (AI) is significantly transforming scientific research. Explainable AI
methods, such as concept-based models (CMs), are promising for driving new scientific …
methods, such as concept-based models (CMs), are promising for driving new scientific …
Interpretable Prognostics with Concept Bottleneck Models
Deep learning approaches have recently been extensively explored for the prognostics of
industrial assets. However, they still suffer from a lack of interpretability, which hinders their …
industrial assets. However, they still suffer from a lack of interpretability, which hinders their …