Abstract
Most deep architectures for image classification–eventhose that are trained to classify a large number of diversecategories–learn shared image representations with a sin-gle model. Intuitively, however, categories that are more similar should share more information than those that are very different. While hierarchical deep networks address this problem by learning separate features for subsets of related categories, current implementations require simplified models using fixed architectures specified via heuristic clustering methods. Instead, we propose Blockout, a method for regularization and model selection that simultaneously learns both the model architecture and parameters. A generalization of Dropout, our approach gives a novel parametrization of hierarchical architectures that allows for structure learning via back-propagation. To demon-strate its utility, we evaluate Blockout on the CIFAR and ImageNet datasets, demonstrating improved classification accuracy, better regularization performance, faster training, and the clear emergence of hierarchical network structures.