paper-with-me

Papers

Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speech

2024-06-11 · Yin-Long Liu, Rui Feng, Jia-Hong Yuan, Zhen-Hua Ling

We uncover an underlying bias present in the audio recordings produced from the picture description task of the Pitt corpus, the largest publicly accessible database for Alzheimer's Disease (AD) detection research. Even by solely utilizing the silent segments of these audio recordings, we achieve nearly 100% accuracy in AD detection. However, employing the same methods to other datasets and preprocessed Pitt recordings results in typical levels (approximately 80%) of AD detection accuracy. These results demonstrate a Clever Hans effect in AD detection on the Pitt corpus. Our findings emphasize the crucial importance of maintaining vigilance regarding inherent biases in datasets utilized for training deep learning models, and highlight the necessity for a better understanding of the models' performance.

📄 PDF Abstract BibTeX arXiv:2406.07410

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Clever Hans Effect in Anomaly Detection

2020-06-18 · Jacob Kauffmann, Lukas Ruff, Grégoire Montavon, Klaus-Robert Müller

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…

Anomaly DetectionExplainable Artificial Intelligence (XAI)Outlier Detection

Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks

2023-04-12 · Lorenz Linhardt, Klaus-Robert Müller, Grégoire Montavon

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) hav…

The Clever Hans Effect in Unsupervised Learning

2024-08-15 · Jacob Kauffmann, Jonas Dippel, Lukas Ruff, Wojciech Samek 외

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…

Making deep neural networks right for the right scientific reasons by interacting with their explanations

2020-01-15 · Patrick Schramowski, Wolfgang Stammer, Stefano Teso, Anna Brugger 외

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 per…

BIG-bench Machine LearningPlant Phenotyping

Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples

2025-10-20 · Sidney Bender, Ole Delzer, Jan Herrmann, Heike Antje Marxfeld 외 arxiv

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 robus…

Knowledge Distillation