These models cover your image-based workflows, such as image classification, object detection, and semantic segmentation. Most networks, including the basic models above, fall into this category. The difference from basic models is that higher-accuracy models may require more training time and have a more complicated network structure.
Start here: ResNet-50, Inception-v3, Densenet-201, Xception
Object detection workflows. DarkNet-19 and DarkNet-53 are often recommended as the foundation for detection and YOLO type workflows. I’ve also seen ResNet-50 used with Faster R-CNN, so there’s some flexibility here too. We’ll get into more details on object detection in the questions below.
Semantic segmentation. You can take a network and turn it into a semantic segmentation network. There are also specific Segnet structures, such as segnetLayers and unetLayers.