Deep Learning for Computer Vision

The Fully Convolutional Network

The Fully Convolutional Network (FCN) introduced the idea of an end-to-end convolutional network. Any standard CNN architecture can be used for FCN by removing the fully connected layers, and the implementation of the same was shown in Chapter 4, Object Detection. The fully connected layers are replaced by a convolution layer. The depth is higher in the final layers and the size is smaller. Hence, 1D convolution can be performed to reach the desired number of labels. But for segmentation, the spatial dimension has to be preserved. Hence, the full convolution network is constructed without a max pooling, as shown here:

The loss for this network is computed by averaging the cross-entropy loss of every pixel ...