Marina M.-C. Höhne — accepted AI-conference papers

2025

Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution

Carlos Eiras-Franco, Anna Hedström, Marina M.-C. Höhne

AAAI 2025technical

Obtaining high-quality explanations of a model's output enables developers to identify and correct biases, align the system's behavior with human values, and ensure ethical compliance. Explainable Artificial Intelligence (XAI) practitioners rely on specific measures to gauge the quality of such expl…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

NoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights

Kirill Bykov, Anna Hedström, Shinichi Nakajima, Marina M.-C. Höhne

AAAI 2022technical

Many efforts have been made for revealing the decision-making process of black-box learning machines such as deep neural networks, resulting in useful local and global explanation methods. For local explanation, stochasticity is known to help: a simple method, called SmoothGrad, has improved the vis…

Cited by 44 Source ↗PDF ↗code ↗Scholar ↗