Method of outputting prediction result using neural network, method of generating neural network, and apparatus therefor
A method of generating a second neural network model according to an example embodiment includes: inputting unlabeled input data to a first neural network model; obtaining prediction results corresponding to the unlabeled input data based on the first neural network model; and generating a second neural network model based on the prediction results of the first neural network model and a degree of distribution of the prediction results.
1. A method of generating a neural network model, the method comprising:
inputting unlabeled input data to a first neural network model;
predicting a class label of the unlabeled input data by obtaining prediction results corresponding to the unlabeled input data based on the first neural network model;
obtaining a posterior distribution of the prediction results, wherein a greater degree of the posterior distribution of the prediction results indicates a greater uncertainty in the class label; and
generating a second neural network model based on the prediction results and a degree of the posterior distribution of the prediction results,
wherein the first neural network model comprises a plurality of nodes, and the obtaining the posterior distribution comprises:
randomly dropping out at least a portion of the plurality of nodes of the first neural network model to repeatedly obtain the prediction results corresponding to the unlabeled input data;
obtaining an average of the repeatedly obtained prediction results; and
determining a pseudo label of the unlabeled input data based on the average of the prediction results.
2. The method of claim 1 , wherein the generating the second neural network model comprises:
training the second neural network model based on a value obtained by multiplying the prediction results of the first neural network model by the degree of the posterior distribution of the prediction results.
3. The method of claim 1 , wherein the training comprises:
training the second neural network model by applying a weight to the prediction results, the weight being proportional to the degree of the posterior distribution of the prediction results.
4. The method of claim 1 , wherein the obtaining comprises, in response to the unlabeled input data being an image:
predicting a class of an object included in the unlabeled input data; and
predicting a bounding box for detecting the object included in the unlabeled input data.
5. The method of claim 1 , wherein the obtaining comprises, in response to the unlabeled input data being voice:
recognizing the voice included in the unlabeled input data.
6. The method of claim 1 , wherein the generating comprises generating the second neural network model that corresponds to a result of on-device learning based on the first neural network model or a result of domain adaptation based on the first neural network model.
7. A non-transitory computer readable storage medium storing computer program, which, when executed by at least one processor, causes the at least one processor to execute the method of claim 1 .
8. An apparatus for generating a neural network model, the apparatus comprising:
a communication interface configured to receive unlabeled input data; and
at least one processor configured to:
input the unlabeled input data to a first neural network model;
predict a class label of the unlabeled input data by obtaining prediction results corresponding to the unlabeled input data based on the first neural network model;
obtain a posterior distribution of the prediction results, wherein a greater degree of the posterior distribution of the prediction results indicates a greater uncertainty in the class label; and
generate a second neural network model based on the prediction results and a degree of the posterior distribution of the prediction results,
wherein the first neural network model comprises a plurality of nodes, and the at least one processor is configured to:
randomly drop out at least a portion of the plurality of nodes of the first neural network model to repeatedly obtain the prediction results corresponding to the unlabeled input data;
obtain an average of the repeatedly obtained prediction results; and
determine a pseudo label of the unlabeled input data based on the average of the prediction results.
9. The apparatus of claim 8 , wherein the at least one processor is configured to train the second neural network model based on a value obtained by multiplying the prediction results of the first neural network model by the degree of the posterior distribution of the prediction results.
10. The apparatus of claim 9 , wherein the at least one processor is configured to train the second neural network model by applying a weight to the prediction results, the weight being proportional to the degree of the posterior distribution of the prediction results.
11. The apparatus of claim 8 , wherein the at least one processor, in response to the unlabeled input data being an image, is configured to:
predict a class of an object included in the unlabeled input data; and
predict a bounding box for detecting the object included in the unlabeled input data, or predict the class of the object included in the unlabeled input data and the bounding box for detecting the object included in the unlabeled input data.
12. The apparatus of claim 8 , wherein the at least one processor, in response to the unlabeled input data being voice, is configured to recognize the voice included in the unlabeled input data.