Diagnostic tool for deep learning similarity models
US12112517B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 14, 2023 |
| Grant date | Oct 8, 2024 |
| Priority date | — |
| Expiry date | Jul 14, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A diagnostic tool for deep learning similarity models and image classifiers provides valuable insight into neural network decision-making. A disclosed solution generates a saliency map by: receiving a test image; determining, with an image classifier, an image classification of the test image; determining, for the test image, a first activation map for at least one model layer using the determined image classification; determining, for the test image, a first gradient map for the at least one model layer using the determined image classification; and generating a first saliency map as an element-wise function of the first activation map and the first gradient map.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.