Following the unsupervised literature [4, 3, 5], the siamese networkFθ is trained by imposing structural properties on the fmapC such as bijectivity and orthogonality on the shape pairs in the training set.

Neural Information Processing Systems http://nips.cc/

That is, thestrong (s( )= k k1) andweakinstantiations (s( )= sum( )) coincideforone-layerneural networks.