Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising
field of research, since explanations that refer to concepts (ie, semantically meaningful parts …
field of research, since explanations that refer to concepts (ie, semantically meaningful parts …
GCPV: Guided Concept Projection Vectors for the Explainable Inspection of CNN Feature Spaces
For debugging and verification of computer vision convolutional deep neural networks
(CNNs) human inspection of the learned latent representations is imperative. Therefore …
(CNNs) human inspection of the learned latent representations is imperative. Therefore …
Closing the loop with concept regularization
AF Posada-Moreno, S Trimpe - DataNinja sAIOnARA …, 2024 - biecoll.ub.uni-bielefeld.de
Abstract Convolutional Neural Networks (CNNs) are widely adopted in industrial settings,
but are prone to biases and lack transparency. Explainable Artificial Intelligence (XAI) …
but are prone to biases and lack transparency. Explainable Artificial Intelligence (XAI) …
Concept extraction for time series with ECLAD
A Holzapfel, AF Posada-Moreno… - DataNinja sAIOnARA …, 2024 - biecoll.ub.uni-bielefeld.de
Abstract Concept Extraction (CE) methods are being increasingly used in the image domain
for explaining deep learning models, which are not inherently interpretable. However, there …
for explaining deep learning models, which are not inherently interpretable. However, there …