| CPC G06V 10/80 (2022.01) [G06V 10/26 (2022.01); G06V 10/82 (2022.01)] | 3 Claims |
|
1. An information processing method that generates a learned model for image recognition, wherein a learning model comprises a plurality of first models and a second model that is different from the first models, the method comprising, by a processor:
dividing an image that is to be used in learning into a plurality of patches;
inputting each of the divided plurality of patches into a respective model of the plurality of first models, the respective model being predetermined for each of the patches, and performing calculation; and
combining an output of a calculation result of each of the plurality of first models in the second model and generating a learned model by learning the learning model,
wherein the second model receives and combines the output of the calculation results of the plurality of first models, calculates a loss of the second model, and learns the learning model,
wherein the learning model further comprises a third model,
wherein the third model receives the output of each of the plurality of first models and calculates an individual loss for each of the outputs, and
wherein an overall loss is calculated based on the individual losses and the loss of the second model and the learning model is learnt.
|