US 10,891,524 B2
Method and an apparatus for evaluating generative machine learning model
Mikko Honkala, Espoo (FI); Francesco Cricri, Tampere (FI); and Xingyang Ni, Tampere (FI)
Assigned to Nokia Technologies Oy, Espoo (FI)
Filed by Nokia Technologies Oy, Espoo (FI)
Filed on Jun. 25, 2018, as Appl. No. 16/17,742.
Claims priority of application No. 1710877 (GB), filed on Jul. 6, 2017.
Prior Publication US 2019/0012581 A1, Jan. 10, 2019
Int. Cl. G06K 9/62 (2006.01); G06K 9/72 (2006.01); G06N 3/08 (2006.01); G06N 3/04 (2006.01)
CPC G06K 9/6265 (2013.01) [G06K 9/6212 (2013.01); G06K 9/726 (2013.01); G06N 3/04 (2013.01); G06N 3/0445 (2013.01); G06N 3/0454 (2013.01); G06N 3/0472 (2013.01); G06N 3/0481 (2013.01); G06N 3/088 (2013.01)] 19 Claims
OG exemplary drawing
1. A method, comprising:
receiving a set of input samples, said set of input samples comprising real images and generated images;
extracting a set of feature maps from multiple layers of a pre-trained neural network for both the real images and the generated images;
determining respective statistics for feature maps of the set of feature maps;
comparing respective statistics of the feature maps for the real images with corresponding respective statistics of the feature maps for the generated images, wherein the comparing of the statistics comprises using a distance function to obtain a vector of distances; and
averaging distances of the vector of distances to have a value providing information about a level of diversity of the generated images.