Information processing apparatus, image capturing apparatus, method, and non-transitory computer readable storage medium

1 . An information processing apparatus comprising:

a shifting unit configured to shift an output of an activation function corresponding to an input, based on an output range of the activation function;

a scaling unit configured to scale the output of the activation function, the output of the activation function having been shifted by the shifting unit; and

an output unit configured to output an output value corresponding to the output of the activation function, the output of the activation function having been scaled by the scaling unit,

wherein:

the activation function is a function in which the minimum value of the output of the activation function corresponding to the input is equal to or larger than a predetermined value,

the output unit outputs a map, based on either the shifted output of the activation function or the scaled output of the activation function, and

the information processing apparatus further comprises an updating unit configured to update a parameter of a learning model that infers from the output value, based on a difference between the map output by the output unit and correct answer data.

2 . The information processing apparatus according to claim 1 , wherein the shifting unit shifts the output of the activation function based on a shift value obtained from a difference between the maximum value and the minimum value in the output range of the activation function.

3 . The information processing apparatus according to claim 1 , wherein the scaling unit determines whether or not to scale, by using a scale value, the shifted output of the activation function, based on whether or not the shifted output of the activation function has exceeded a threshold value.

4 . The information processing apparatus according to claim 1 , further comprising a control unit configured to store, in a memory, the parameter of the learning model, the parameter being updated by the updating unit.

5 . The information processing apparatus according to claim 1 , wherein the map includes:

a likelihood map representing an estimation result indicating a position where a subject exists in a search image with a high probability,

a size map representing an estimation result of a width and a height of the subject, and

a positional deviation map representing an estimation result of a positional deviation of the subject in a region including a first pixel in the likelihood map and pixels in the vicinity of the first pixel.

6 . The information processing apparatus according to claim 1 , wherein the updating unit determines, based on the difference, a scale value used for scaling the output of the activation function by the scaling unit.

7 . The information processing apparatus according to claim 1 , wherein the updating unit determines a scale value based on comparison between the shifted output range of the activation function and a threshold value.

8 . The information processing apparatus according to claim 1 , further comprising a calculation unit configured to calculate a loss based on a likelihood map representing an estimation result indicating a position where a subject exists in a search image with a high probability, and the correct answer data, wherein

the updating unit determines a scale value based on the loss and the correct answer data.

9 . A method comprising:

shifting an output of an activation function corresponding to an input, based on an output range of the activation function;

scaling the output of the activation function, the output of the activation function having been shifted; and

outputting an output value corresponding to the output of the activation function, the output of the activation function having been scaled,

wherein:

the activation function is a function in which the minimum value of the output of the activation function corresponding to the input is equal to or larger than a predetermined value,

a map is output in the outputting, based on either the shifted output of the activation function or the scaled output of the activation function, and

the method further comprises updating a parameter of a learning model that infers from the output value, based on a difference between the map output in the outputting and correct answer data.

10 . A non-transitory computer-readable storage medium storing a program that, when executed by a computer, causes the computer to perform a method comprising:

shifting an output of an activation function corresponding to an input, based on an output range of the activation function;

scaling the output of the activation function, the output of the activation function having been shifted; and

outputting an output value corresponding to the output of the activation function, the output of the activation function having been scaled,

wherein:

the activation function is a function in which the minimum value of the output of the activation function corresponding to the input is equal to or larger than a predetermined value,

a map is output in the outputting, based on either the shifted output of the activation function or the scaled output of the activation function, and

the method further comprises updating a parameter of a learning model that infers from the output value, based on a difference between the map output in the outputting and correct answer data.

11 . An image capturing apparatus comprising:

an image capturing unit configured to capture an image of a subject; and

an information processing apparatus comprising:

a shifting unit configured to shift an output of an activation function corresponding to an input, based on an output range of the activation function;

a scaling unit configured to scale the output of the activation function, the output of the activation function having been shifted by the shifting unit; and

an output unit configured to output an output value corresponding to the output of the activation function, the output of the activation function having been scaled by the scaling unit,

wherein:

the activation function is a function in which the minimum value of the output of the activation function corresponding to the input is equal to or larger than a predetermined value,

the output unit outputs a map, based on either the shifted output of the activation function or the scaled output of the activation function, and

the information processing apparatus further comprises an updating unit configured to update a parameter of a learning model that infers from the output value, based on a difference between the map output by the output unit and correct answer data.

12 . The image capturing apparatus according to claim 11 , further comprising an acceptance unit configured to accept specification of the subject to be detected from an image.