December 2018
Intermediate to advanced
764 pages
18h 18m
English
The SegNet has an encoder and decoder approach. The encode has various convolution layers and decoder has various deconvolution layers. SegNet improved the coarse outputs produced by FCN. Because of this, it is less intensive on memory. When the features are reduced in dimensions, it is upsampled again to the image size by deconvolution, reversing the convolution effects. Deconvolution learns the parameters for upsampling. The output of such architecture will be coarse due to the loss of information in pooling layers.

Now, let's learn the few new concepts called upsampling, atrous convolution, and transpose convolution ...
Read now
Unlock full access