2026-05-28T09:31:40Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/323642026-02-03T11:22:02Zcom_10630_2254col_10630_37953

00925njm 22002777a 4500 dc Jose Ángel, Díaz-Francés author Fernández-Rodríguez, Jose David author Thurnhofer-Hemsi, Karl author López-Rubio, Ezequiel author 2024 Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by 4.5% and 5.0%. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to 11% for the binary image segmentation approach. ose Angel Diaz-Frances et al., Semi-supervised semantic image segmen-tation by deep diffusion models and generative adversarial networks, Inter-national Journal of Neural Systems, doi: 10.1142/S0129065724500576 https://hdl.handle.net/10630/32364 10.1142/S0129065724500576 Procesado de imágenes Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks