Contrastive explanations for images with monotonic attribute functions
In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.
1. A computer implemented method for generating contrastive information for a classifier prediction, the computer implemented method comprising:
receiving, by one or more processors, image data representative of an original input image;
creating, by the one or more processors, a modified input image by adding a high-level feature to a copy of the original input image; and
determining, by the one or more processors, using a deep learning classifier model, that the modified input image is a pertinent-negative image that is most similar to the original input image in a set of modified input images, wherein the modified input image has a classification that is different from a classification of the original input image.
2. The computer implemented method of claim 1 , further comprising:
generating, by the one of more processors, a report that includes a visual representation of the pertinent-negative image.
3. The computer implemented method of claim 1 , further comprising:
creating, by the one or more processors, a pertinent-positive image that is a modified version of the original input image and that includes fewer than all superpixels of the original input image while still being predicted by the deep learning classifier model to be in the classification of the original input image.
4. The computer implemented method of claim 3 , further comprising:
comparing a plurality of modified images to identify a candidate modified image that has an amount of the original input image remaining while still being classified in the classification of the original input image, wherein each of the plurality of modified images is a modified version of the original input image having fewer than all portions of the input image.
5. The computer implemented method of claim 1 , wherein the determining of the pertinent-negative image includes determining that the pertinent-negative image is a result with a smallest change to the original input image from among other potential modifications to the original input image.
6. The computer implemented method of claim 1 , wherein the original input image is a multiple-color image.
7. The computer implemented method of claim 1 , wherein the determining includes identifying that the pertinent-negative image will be classified by the deep learning classifier model as a second classification that is different from a first classification of the original input image.
8. A computer usable program product for generating contrastive information for a classifier prediction, the computer usable program product comprising a computer-readable storage device, and program instructions stored on the storage device, the stored program instructions comprising:
program instructions to receive, by one or more processors, image data representative of an original input image;
program instructions to create, by the one or more processors, a modified input image by adding a high-level feature to a copy of the original input image; and
program instructions to determine, by the one or more processors, using a deep learning classifier model, that the modified input image is a pertinent-negative image that is most similar to the original input image in a set of modified input images, wherein the modified input image has a classification that is different from a classification of the original input image.
9. A computer usable program product of claim 8 , further comprising program instructions to generate, by the one or more processors, a report that includes a visual representation of the pertinent-negative image.
10. A computer usable program product of claim 8 , further comprising:
program instructions to create, by the one or more processors, a pertinent-positive image that is a modified version of the original input image and that includes fewer than all superpixels of the original input image while still being predicted by the deep learning classifier model to be in the classification of the original input image.
11. A computer usable program product of claim 10 , further comprising:
program instructions to compare a plurality of modified images to identify a candidate modified image that has an amount of the original input image remaining while still being classified in the classification of the original input image, wherein each of the plurality of modified images is a modified version of the original input image having fewer than all portions of the input image.
12. A computer usable program product of claim 8 , wherein the program instructions to determine the pertinent-negative image includes program instructions to determine that the pertinent-negative image is a result with a smallest change to the original input image from among other potential modifications to the original input image.
13. A computer usable program product of claim 8 , wherein the input image is a multiple-color image.
14. A computer usable program product of claim 8 , wherein the program instructions to determine includes program instructions to identify that the pertinent-negative image will be classified by the deep learning classifier model as a second classification that is different from a first classification of the original input image.
15. A computer system comprising a processor, a computer-readable memory, and a computer-readable storage device, and program instructions stored on the storage device for execution by the processor via the memory, the stored program instructions comprising:
program instructions to receive, by one or more processors, image data representative of an original input image;
program instructions to create, by the one or more processors, a modified input image by adding a high-level feature to a copy of the original input image; and
program instructions to determine, by the one or more processors, using a deep learning classifier model, that the modified input image is a pertinent-negative image that is most similar to the original input image in a set of modified input images, wherein the modified input image has a classification that is different from a classification of the original input image.
16. The computer system of claim 15 , further comprising
program instructions to generate, by the one or more processors, a report that includes a visual representation of the pertinent-negative image.
17. The computer system of claim 15 , further comprising:
program instructions to create, by the one or more processors, a pertinent-positive image that is a modified version of the original input image and that includes fewer than all superpixels of the original input image while still being predicted by the deep learning classifier model to be in the classification of the original input image.
18. The computer system of claim 17 , further comprising:
program instructions to compare a plurality of modified images to identify a candidate modified image that has an amount of the original input image remaining while still being classified in the classification of the original input image, wherein each of the plurality of modified images is a modified version of the original input image having fewer than all portions of the input image.
19. The computer system of claim 15 , wherein the program instructions to determine the pertinent-negative image includes program instructions to determine that the pertinent-negative image is a result with a smallest change to the original input image from among other potential modifications to the original input image.
20. The computer system of claim 15 , wherein the program instructions to determine includes program instructions to identify that the pertinent-negative image will be classified by the deep learning classifier model as a second classification that is different from a first classification of the original input image.