RT Journal Article
T1 Enhanced generation of automatically labelled image segmentation datasets by advanced style interpreter deep architectures.
A1 Pacheco dos Santos Lima Junior, Marcos Sergio
A1 López-Rubio, Ezequiel
A1 Ortiz-de-Lazcano-Lobato, Juan Miguel
A1 Fernández-Rodríguez, Jose David
K1 Redes neuronales artificiales
K1 Aprendizaje automático (Inteligencia artificial)
AB Large image datasets with annotated pixel-level semantics are necessary to train and evaluate supervised deep-learning models. These datasets are very expensive in terms of the human effort required to build them. Still, recent developments such as DatasetGAN open the possibility of leveraging generative systems to automatically synthesise massive amounts of images along with pixel-level information. This work analyses DatasetGAN and proposes a novel architecture that utilises the semantic information of neighbouring pixels to achieve significantly better performance. Additionally, the overfitting observed in the original architecture is thoroughly investigated, and modifications are proposed to mitigate it. Furthermore, the implementation has been redesigned to greatly reduce the memory requirements of DatasetGAN, and a comprehensive study of the impact of the number of classes in the segmentation task is presented.
PB Elsevier
YR 2025
FD 2025
LK https://hdl.handle.net/10630/38505
UL https://hdl.handle.net/10630/38505
LA eng
NO Marcos Sergio Pacheco dos Santos Lima, Ezequiel López-Rubio, Juan Miguel Ortiz-de-Lazcano-Lobato, José David Fernández-Rodríguez, Enhanced generation of automatically labelled image segmentation datasets by advanced style interpreter deep architectures, Pattern Recognition Letters, Volume 193, 2025, Pages 101-107
NO Funding for open access charge: Universidad de Málaga / CBUA
NO This work is partially supported by the Ministry of Science and Innovation of Spain [grant number PID2022-136764OA-I00], project name Automated Detection of Non Lesional Focal Epilepsy by Probabilistic Diffusion Deep Neural Models. It is also partially supported by the Autonomous Government of Andalusia (Spain) under project UMA18-FEDERJA-084, project name Detection of anomalous behaviour agents by deep learning in low-cost video surveillance intelligent systems. All of them include funds from the European Regional Development Fund (ERDF).
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 25 ene 2026