There are two types of deep neural networks, Base network, and detection network. MobileNet, VGG-Net, LeNet are base networks.
The base network provides high-level features for classification or detection. If you use an entirely connected layer at the end of these networks, you have a classification. But you can remove a fully connected layer and replace it with detection networks, like SSD, Faster R-CNN, and so on. In general, SSD use of last convolutional layer on base networks for the detection task. MobileNet just like other base networks uses of convolution to produce high-level features.
For more insights on this, study the Types Of Machine Learning Courses. Also, this problem would be solved while going through the Neural Network Tutorial.
Hope this answer helps you!