Balancing misclassification errors in image-based inference using problem domain semantics and a nested cascade architecture.

Pattern recognition models, particularly neural networks, often focus on maximising classification accuracy. However, in practice, the types of errors made (misclassification between different classes) can have varying associated costs. Current methods overlook varying misclassification error types. Misclassification labels can either be available from expert knowledge or derived from semantics of textual descriptions of class labels. Exploiting such misclassification costs can have significant implications when deploying machine learning systems. Here, using five examples from image and tabular domains, we show how a deep neural architecture trained in a nested layer-wise fashion (cascade learning) in which early layers solve easier problems than later ones could exploit such hierarchical aspects of class labels. We employ a measure of performance called "severity" of errors and show how emphasis could be placed on classes that are deeper in the hierarchy, ignoring errors that arise between semantic neighbours. Supplementary Information: The online version contains supplementary material available at 10.1007/s00521-025-11613-8.