Figure 2
From: A novel approach for automatic classification of macular degeneration OCT images
Illustrates the structure of the MSA-Net model. The model consists primarily of three parts: (a) encoder, (b) inverted residual modules, and (c) classifier. The input encoder transforms the input image into feature maps through convolution, the inverted residual modules enhance the representations of the feature maps, and finally, the classifier computes the probability of each input image belonging to a particular class.
