English
Related papers

Related papers: Finding and Removing Clever Hans: Using Explanatio…

200 papers

Unsupervised learning has become an essential building block of AI systems. The representations it produces, e.g. in foundation models, are critical to a wide variety of downstream applications. It is therefore important to carefully…

Machine Learning · Computer Science 2025-03-18 Jacob Kauffmann , Jonas Dippel , Lukas Ruff , Wojciech Samek , Klaus-Robert Müller , Grégoire Montavon

Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have…

Machine Learning · Computer Science 2024-04-16 Dilyara Bareeva , Maximilian Dreyer , Frederik Pahde , Wojciech Samek , Sebastian Lapuschkin

Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain knowledge (e.g. Clever Hans effects) have been identified as…

Machine Learning · Computer Science 2023-11-13 Lorenz Linhardt , Klaus-Robert Müller , Grégoire Montavon

The 'Clever Hans' effect occurs when the learned model produces correct predictions based on the 'wrong' features. This effect which undermines the generalization capability of an ML model and goes undetected by standard validation…

Machine Learning · Computer Science 2020-06-19 Jacob Kauffmann , Lukas Ruff , Grégoire Montavon , Klaus-Robert Müller

Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data condition that…

Machine Learning · Computer Science 2025-11-03 Jakob Hackstein , Sidney Bender

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning…

Artificial Intelligence · Computer Science 2019-02-28 Sebastian Lapuschkin , Stephan Wäldchen , Alexander Binder , Grégoire Montavon , Wojciech Samek , Klaus-Robert Müller

Deep neural networks have shown excellent performances in many real-world applications. Unfortunately, they may show "Clever Hans"-like behavior -- making use of confounding factors within datasets -- to achieve high performance. In this…

Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-supervised models. Group distributional robustness methods, such…

Machine Learning · Computer Science 2026-05-07 Sidney Bender , Ole Delzer , Jan Herrmann , Heike Antje Marxfeld , Klaus-Robert Müller , Grégoire Montavon

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

Machine Learning · Computer Science 2022-02-08 Yujiang He

Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is…

Machine Learning · Computer Science 2026-04-07 Ole Delzer , Sidney Bender

Explainable Artificial Intelligence has gained significant attention due to the widespread use of complex deep learning models in high-stake domains such as medicine, finance, and autonomous cars. However, different explanations often…

Artificial Intelligence · Computer Science 2024-04-17 Weronika Hryniewska-Guzik , Luca Longo , Przemysław Biecek

Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zubair Faruqui , Rahul Dubey

A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, these methods often perform poorly in the face of biased data,…

Machine Learning · Computer Science 2022-02-02 Xiaoting Shao , Karl Stelzner , Kristian Kersting

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This…

Machine Learning · Computer Science 2020-09-10 Maruan Al-Shedivat , Avinava Dubey , Eric P. Xing

In the realm of human activity recognition (HAR), the integration of explainable Artificial Intelligence (XAI) emerges as a critical necessity to elucidate the decision-making processes of complex models, fostering transparency and trust.…

Artificial Intelligence · Computer Science 2024-08-22 Yiran Huang , Yexu Zhou , Haibin Zhao , Till Riedel , Michael Beigl

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

Machine Learning · Computer Science 2018-10-03 Andrew Slavin Ross

Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover,…

Machine Learning · Computer Science 2021-06-22 Wolfgang Stammer , Patrick Schramowski , Kristian Kersting

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Andrea Zunino , Sarah Adel Bargal , Riccardo Volpi , Mehrnoosh Sameki , Jianming Zhang , Stan Sclaroff , Vittorio Murino , Kate Saenko

Artificial Intelligence (AI) is often an integral part of modern decision support systems. The best-performing predictive models used in AI-based decision support systems lack transparency. Explainable Artificial Intelligence (XAI) aims to…

Machine Learning · Computer Science 2025-02-25 Tuwe Löfström , Helena Löfström , Ulf Johansson , Cecilia Sönströd , Rudy Matela

Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are…

Machine Learning · Computer Science 2024-04-16 Pattarawat Chormai , Jan Herrmann , Klaus-Robert Müller , Grégoire Montavon
‹ Prev 1 2 3 10 Next ›