Reviews: Distributed Weight Consolidation: A Brain Segmentation Case Study

The paper proposes a technique for learning a model by consolidating weights across models that are trained in different datasets. The proposed approach thus attempts to solve an important problem that arises by the limitations of sharing and pooling data. The authors take on the brain segmentation problem by using MeshNet architectures. The proposed method essentially starts from the model learned from one dataset, performs variational continual learning to parallel train across multiple datasets, and then performs bayesian parallel learning to fine tune the model on a dataset by using as prior the weights learned in parallel from the rest of the datasets. The proposed approach has been tested using free surfer segmentations for data part of the Human Connectome Project, the Nathan Kline Institute, the Buckner Lab and the ABIDE project.