Large-Scale Coarse-to-Fine Object Retrieval Ontology and Deep Local Multitask Learning

Figure 16

Best normal cells and reduction cells identified with CIFAR-10 and ImageNet architecture (right) are built from the best convolutional cells [36]. Zoph et al. built two types of cells because they want to create architectures for images of any size. While normal cells return a feature map which has the same dimension, reduction cells return a feature map with height and width reduced by a factor of two.