The original meaning of the word backbone refers to the backbone of a person, but it was later extended to the backbone, the core.
In neural networks, especially in the field of CV, image features are generally extracted first (commonly include vggnet, resnet, and Google’s inception). This part is the foundation of the entire CV task, because subsequent downstream tasks are based on extraction. Image features to make a fuss (such as classification, generation, etc.).
So it is very vivid to call this part of the network structure the backbone, as if it is a pillar for a person to stand up.
The meaning of feature map in convolutional neural network
In each convolutional layer, data exists in three-dimensional form. You can think of it as many two-dimensional pictures stacked together, each of which is called a feature map. In the input layer, if it is a grayscale image, there is only one feature map; if it is a color image, there are generally three feature maps (red, green and blue). There will be several convolution kernels (kernels) between layers. The upper layer and each feature map are convolved with each convolution kernel, and a feature map of the next layer will be generated.
I am just a useless learning tool for extracting others