Data augmentation for image classification tasks

1. A computer program product for performing machine learning for an image classification task, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

overlaying, by a processor, a second image on a first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image; and

training, by the processor, a machine learning process configured for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

2. The computer program product of claim 1 , wherein said training step comprises using a label of the first image as a label of the mixed image.

3. The computer program product of claim 1 , wherein said training step comprises using a label of the second image as a label of the mixed image.

4. The computer program product of claim 1 , wherein said training step comprises mixing a label of the first image and a label of the second image to form a label of the mixed image.

5. The computer program product of claim 1 , wherein said selecting and overlaying steps are part of a data augmentation process used for training the machine learning process in said training step, and wherein said data augmentation process is selectively disabled and enabled at one or more time periods to increase a training speed.

6. The computer program product of claim 5 , wherein the one or more time periods comprise multiple consecutive time periods, a first one of the multiple consecutive time periods corresponding to a commencement of a training stage for training the machine learning process.

7. The computer program product of claim 5 , wherein the one or more time periods are at intermediate periods in a training stage for training the machine learning process.

8. The computer program product of claim 1 , wherein the image classification task relates to a surveillance system and the method further comprises:

applying the trained machine learning process to a test image to obtain a classification for the test image; and

actuating a lock on a door to keep an identified object from a target area, responsive to the classification for the test image.

9. A computer processing system for performing machine learning for an image classification task, comprising:

a processor configured to

overlay a second image on a first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image; and

train a machine learning process for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

10. The computer processing system of claim 9 , wherein the machine learning process is trained for the image classification task using a label of the first image as a label of the mixed image.

11. The computer processing system of claim 9 , wherein the machine learning process is trained for the image classification task using a label of the second image as a label of the mixed image.

12. The computer processing system of claim 9 , wherein the machine learning process is trained for the image classification task by mixing a label of the first image and a label of the second image to form a label of the mixed image.

13. An advanced driver-assistance system for a motor vehicle, comprising:

a camera configured to capture an actual image relating to an external view from the motor vehicle; and

a processor configured to

overlay a second image on a first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image;

perform machine learning by training a machine learning process configured for an image classification task using the mixed image to augment data used by the machine learning process for the image classification task, the image classification task relating to a driver-assistance function;

apply the trained machine learning process to the test image to obtain a classification for the test image; and

control a function of one or more hardware devices of the motor vehicle, responsive to the classification for the test image.