Components of STN - rugbyprof/5443-Data-Mining GitHub Wiki

What are the three components of STN?

Localization network:

(General Def)It will estimate which are the best parameters given the input data should be applied to this transformation

Takes the feature map as input and outputs the parameters of the affine transformation that should be applied to that feature map.

Grid generator:

(General Def)It Basically defines what kind of transformation to be applied

Generates a grid of (x,y) coordinates using the parameters of the affine transformation that corresponds to a set of points where the input feature map should be sampled to produce the transformed output feature map.

Sampler:

(General Def) It Does Some operations that will solve this problem with the values that are not defined.After Transformations are done the resultant feature map is gone through this phase to take the errors out of the input feature map

Takes as input the input feature map and the grid generated by the grid generator and produces the output feature map using bilinear interpolation.

---