TOSCARIZER: Generate TOSCA files for the AI-SPRINT project read more of TOSCARIZER

Transparent parallelisation of user code and seamless execution of the same code on different backends from the edge to the cloud and HPC clusters. read more of PyCOMPSs and dislib

Two efficient variants to compute the differentiable matrix square root. read more of Fast Differentiable Matrix Square Root

A novel ECGAN for the challenging semantic image synthesis task read more of Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis

We address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains. We identify two key aspe... read more of Curriculum Graph Co-Teaching for Multi-target Domain Adaptation

A novel approach for class-iNCD which prevents forgetting of past information about the base classes by jointly exploiting base class feature prototypes and feature-level knowledge distillation. read more of class-incremental Novel Class Discovery

A novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the challenging person image generation task. read more of Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis

A Pytorch-based batch-efficient ED solver for small and medium matrices (dim<32), which is dedicated to the application scenarios of computer vision. read more of Batch-efficient EigenDecomposition for Small and Medium Matrices

An augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, (SoftClu). read more of Augmentation-free unsupervised approach for point clouds

A new Attention-Guided Generative Adversarial Network (AttentionGAN) for the unpaired image to image translation task. read more of AttentionGAN: Unpaired Image-to-Image Translation