Search Results for author:
Found 12 papers, 1 papers with code
The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
Adversarial attacks (AAs) pose a significant threat to the reliability and robustness of deep neural networks.
GCPV: Guided Concept Projection Vectors for the Explainable Inspection of CNN Feature Spaces
The latter, though, is of particular interest for debugging, like finding and understanding outliers, learned notions of sub-concepts, and concept confusion.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes
In this work, we extend beyond identifying OoD road obstacles in video streams and offer a comprehensive approach to extract sequences of OoD road obstacles using text queries, thereby proposing a way of curating a collection of OoD data for subsequent analysis.
Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces
These allow insights into both the flow and likeness of semantic information within CNN layers, and into the degree of their similarity between different network architectures.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
The guiding use-case is a post-hoc explainability framework for object detection (OD) CNNs, towards which existing concept analysis (CA) methods are successfully adapted.
Dimensionality Reduction
Explainable artificial intelligence
+4
Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey
The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models.
Concept Embedding Analysis: A Review
The research field of concept (embedding) analysis (CA) tackles this problem: CA aims to find global, assessable associations of humanly interpretable semantic concepts (e. g., eye, bearded) with internal representations of a DNN.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings
In this work, we present a simple, yet effective, approach to verify that a CNN complies with symbolic predicate logic rules which relate visual concepts.
Expressive Explanations of DNNs by Combining Concept Analysis with ILP
We show that our explanation is faithful to the original black-box model.
A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
With the amount of XAI methods vastly growing, a taxonomy of methods is needed by researchers as well as practitioners: To grasp the breadth of the topic, compare methods, and to select the right XAI method based on traits required by a specific use-case context.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Verification of Size Invariance in DNN Activations using Concept Embeddings
One approach to this is concept analysis, which aims to establish a mapping between the internal representation of a DNN and intuitive semantic concepts.
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods.
