Object recognition method and apparatus based on weakly supervised learning

1. An object recognition method based on weakly supervised learning, the method performed by an object recognition apparatus and comprising:

extracting a plurality of feature maps from a training target image given classification result of an object of interest;

generating an activation map for each of the object of interest by accumulating the feature maps;

calculating a representative value of each of the object of interest by aggregating activation values included in a corresponding activation map;

determining an error by comparing classification result determined using the representative value of each of the object of interest with the given classification result; and

updating a convolutional neural network (CNN)-based object recognition model by back-propagating the error,

wherein the generating of the activation map comprises:

determining an activation value at a first location in the activation map using feature values at the first location in the feature maps; and

determining an activation value at a second location in the activation map using feature values at the second location in the feature maps, and

wherein the activation map is an activation map of a first object of interest, and the determining of the activation value at the first location in the activation map comprises adjusting the activation value at the first location in the activation map of the first object of interest to increase a difference between the activation value at the first location in the activation map of the first object of interest and an activation value at the first location in an activation map of a second object of interest different from the first object of interest.

2. The method of claim 1 , wherein the object recognition model comprises:

a convolution layer which extracts a plurality of feature maps from the training target image; and

a deconvolution layer which increases sizes of the feature maps while maintaining a pattern shown in the feature maps.

3. The method of claim 2 , wherein the deconvolution layer is provided in a plurality, and the feature maps comprise at least two feature maps among feature maps input to the deconvolution layers and feature maps output from the deconvolution layers.

4. The method of claim 2 , wherein the feature maps comprise a plurality of feature maps having different sizes, and the generating of the activation map comprises matching the sizes of the feature maps and generating an activation map for each of the object of interest using the matched feature maps.

5. The method of claim 2 , wherein a weight matrix of a filter used in the deconvolution layer is obtained by transposing a weight matrix of a filter used in the convolution layer corresponding to the deconvolution layer.

6. The method of claim 1 , wherein the training target image is a radiographic image, and the object of interest is a lesion.

7. An object recognition apparatus comprising:

one or more processors;

a network interface;

a memory which loads a computer program executed by the processors to perform an object recognition method based on weakly supervised learning; and

a storage which stores the computer program,

wherein the computer program comprises:

an operation of extracting a plurality of feature maps from a training target image given classification result of an object of interest;

an operation of generating an activation map for each of the object of interest by accumulating the feature maps;

an operation of calculating a representative value of each of the object of interest by aggregating activation values included in a corresponding activation map;

an operation of determining an error by comparing classification result determined using the representative value of each of the object of interest with the given classification result; and

an operation of updating a convolutional neural network (CNN)-based object recognition model by back-propagating the error,

wherein the operation of generating of the activation map comprises:

an operation of determining an activation value at a first location in the activation map using feature values at the first location in the feature maps; and

an operation of determining an activation value at a second location in the activation map using feature values at the second location in the feature maps, and

wherein the activation map is an activation map of a first object of interest, and the operation of determining of the activation value at the first location in the activation map comprises an operation of adjusting the activation value at the first location in the activation map of the first object of interest to increase a difference between the activation value at the first location in the activation map of the first object of interest and an activation value at the first location in an activation map of a second object of interest different from the first object of interest.

8. The apparatus of claim 7 , wherein the object recognition model comprises:

a convolution layer which extracts a plurality of feature maps from the training target image; and

a deconvolution layer which increases sizes of the feature maps while maintaining a pattern shown in the feature maps.

9. The apparatus of claim 8 , wherein the deconvolution layer is provided in a plurality, and the feature maps comprise at least two feature maps among feature maps input to the deconvolution layers and feature maps output from the deconvolution layers.

10. The apparatus of claim 8 , wherein the feature maps comprise a plurality of feature maps having different sizes, and the operation of generating of the activation map comprises an operation of matching the sizes of the feature maps and an operation of generating an activation map for each of the object of interest using the matched feature maps.

11. The apparatus of claim 8 , wherein a weight matrix of a filter used in the deconvolution layer is obtained by transposing a weight matrix of a filter used in the convolution layer corresponding to the deconvolution layer.