	US 12,190,556 B2
	Learning apparatus, learning method, and learning program, graph structure extraction apparatus, graph structure extraction method, and graph structure extraction program, and learned extraction model
Deepak Keshwani, Tokyo (JP)
Assigned to FUJIFILM Corporation, Tokyo (JP)
Filed by FUJIFILM Corporation, Tokyo (JP)
Filed on Jan. 21, 2022, as Appl. No. 17/581,836.
Application 17/581,836 is a continuation of application No. PCT/JP2020/028416, filed on Jul. 22, 2020.
Claims priority of application No. 2019-137034 (JP), filed on Jul. 25, 2019.
Prior Publication US 2022/0148286 A1, May 12, 2022
Int. Cl. G06V 10/426 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01)

CPC G06V 10/426 (2022.01) [G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01); G06V 2201/03 (2022.01)]

14 Claims

1. A learning apparatus comprising:

at least one processor, wherein the processor is configured to:

input a learning image and ground-truth data of the learning image to an extraction model, wherein the ground-truth data of the learning image comprises an extraction result of nodes of a graph structure included in the learning image;

receive a feature map for learning outputted from the extraction model such that a feature vector distance between nodes belonging to a same graph structure included in learning image corresponds to a topological distance which is a distance on a route of the graph structure between the nodes;

derive, according to the feature map for learning and the ground-truth data for learning, a loss between the nodes on the graph structure included in the learning image on the basis of a difference between the feature vector distance and the topological distance; and

perform learning of the extraction model on the basis of the loss.