Attributionally robust training for weakly supervised localization and segmentation
US11544495B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 10, 2020 |
| Grant date | Jan 3, 2023 |
| Priority date | — |
| Expiry date | Aug 23, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments are disclosed for training a neural network classifier to learn to more closely align an input image with its attribution map. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training image comprising a representation of one or more objects, the training image associated with at least one label for the representation of the one or more objects, generating a perturbed training image based on the training image using a neural network, and training the neural network using the perturbed training image by minimizing a combination of classification loss and attribution loss to learn to align an image with its corresponding attribution map.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.