3 papers
eess.IV2025
Full-Head Segmentation of MRI with Abnormal Brain Anatomy: Model and Data Release
Andrew M Birnbaum, Adam Buchwald, Peter Turkeltaub +7
Purpose: The goal of this work was to develop a deep network for whole-head segmentation including clinical MRIs with abnormal anatomy, and compile the first public benchmark datas…
cs.NE2024
Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning
Osvaldo M Velarde, Lucas C Parra
Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision…
cs.LG2024
The Role of Fibration Symmetries in Geometric Deep Learning
Osvaldo Velarde, Lucas Parra, Paolo Boldi +1
Geometric Deep Learning (GDL) unifies a broad class of machine learning techniques from the perspectives of symmetries, offering a framework for introducing problem-specific induct…