Enhancing feature compression and reconstruction in time-series and image domains with pseudo-overlap and pseudo-grouping pooling functions

Deep learning techniques are widely used for compressing and reconstructing images and time-series features, thanks to their ability to learn efficient latent representations. In this work, we introduce two families of pooling functions -pseudo-overlap and pseudo-grouping- and integrate them within...

Descripción completa

Detalles Bibliográficos
Autores: Carollo, Matteo, Ferrero Jaurrieta, Mikel, Paiva, Rui, Bardozzo, Francesco, Tagliaferri, Roberto
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Universidad Pública de Navarra
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:dnet:academicae__::bdb7ee9e6791e78d598e56acfb2043e5
Acceso en línea:https://hdl.handle.net/2454/56702
Access Level:acceso abierto
Palabra clave:Aggregation functions
Compression and reconstruction
Deep learning
Feature extraction
Pooling
Descripción
Sumario:Deep learning techniques are widely used for compressing and reconstructing images and time-series features, thanks to their ability to learn efficient latent representations. In this work, we introduce two families of pooling functions -pseudo-overlap and pseudo-grouping- and integrate them within an autoencoder to improve feature extraction and latent space organization. Unlike conventional pooling methods, these functions adaptively modulate feature aggregation, allowing better preservation of structural information during compression. We evaluate the proposed pooling mechanisms on both image (MNIST, FashionMNIST, CIFAR10, SVHN, CIFAR100, ImageNet) and time-series datasets (Vasicek, J-Vasicek, GMB, J-GMB, MRD, J-MRD), demonstrating enhanced reconstruction accuracy. Comparative experiments show that pseudo-overlap and pseudo-grouping outperform traditional pooling layers, especially in datasets with complex structures, highlighting the importance of carefully designing pooling operations for optimal performance.