The COVID-19 pandemic since 2019 has strained healthcare globally. In such a context, chest x-ray images are vital for diagnosis. Automating their classification through Convolutional Neural Networks (CNNs) can save time. In this paper we propose a CNN-based pipeline for diagnosis that focuses on improving information fusion in pooling layers with new aggregation functions. Replacing traditional CNN processes yields varied model behaviors, useful for prioritizing metrics like precision or recall.

Despite numerous studies on pooling algorithms, max-pooling remains the standard choice in CNNs. In this work, we introduce (a, b)-grouping functions, an extension of grouping functions tailored for real-valued data in CNNs. We present various construction methods for (a, b)-grouping functions and empirically demonstrate their effectiveness by replacing max-pooling in popular CNN architectures, yielding promising results. Our findings highlight the potential of grouping functions as efficient alternatives to max-pooling in CNN feature downsampling.

In this work, we replace traditional pooling by several alternative functions. In particular, we consider linear combinations of order statistics and generalizations of the Sugeno integral, extending the latter’s domain to the whole real line and setting the theoretical base for their application. We present an alternative pooling layer based on this strategy which we name “CombPool” layer.