Advancing Out-of-Distribution Detection via Local Neuroplasticity
Eberhard-Karls-Universität Tübingen · Mercedes-Benz AG · CS Department, University of Freiburg, Germany, Albert-Ludwigs-Universität Freiburg · Karlsruher Institut für Technologie · University of Tübingen and MPI for Intelligent Systems · Research&Development
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
In the domain of machine learning, the assumption that training and test data share the same distribution is often violated in real-world scenarios, requiring effective out-of-distribution (OOD) detection. This paper presents a novel OOD detection method that leverages the unique local neuroplasticity property of Kolmogorov-Arnold Networks (KANs). Unlike traditional multilayer perceptrons, KANs exhibit local plasticity, allowing them to preserve learned information while adapting to new tasks. Our method compares the activation patterns of a trained KAN against its untrained counterpart to detect OOD samples. We validate our approach on benchmarks from image and medical domains, demonstrating superior performance and robustness compared to state-of-the-art techniques. These results underscore the potential of KANs in enhancing the reliability of machine learning systems in diverse environments.