公开(公告)号：US20230139927A1

公开(公告)日：2023-05-04

申请号：US18148256

申请日：2022-12-29

Applicant: Adobe Inc.

Inventor： Mayank SINGH ,  Balaji Krishnamurthy ,  Nupur KUMARI ,  Puneet MANGLA

IPC: G06T7/11 ,  G06N3/08 ,  G06N3/04 ,  G06F18/214 ,  G06F18/21 ,  G06V10/774 ,  G06V10/82

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.

公开(公告)号：US20240153258A1

公开(公告)日：2024-05-09

申请号：US17976541

申请日：2022-10-28

Applicant: ADOBE INC.

Inventor： Puneet MANGLA ,  Milan AGGARWAL ,  Balaji KRISHNAMURTHY

IPC: G06V10/80 ,  G06F40/40 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V10/86

CPC classification number: G06V10/811 ,  G06F40/40 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/82 ,  G06V10/86

Abstract: Various embodiments classify one or more portions of an image based on deriving an “intrinsic” modality. Such intrinsic modality acts as a substitute to a “text” modality in a multi-modal network. A text modality in image processing is typically a natural language text that describes one or more portions of an image. However, explicit natural language text may not be available across one or more domains for training a multi-modal network. Accordingly, various embodiments described herein generate an intrinsic modality, which is also a description of one or more portions of an image, except that such description is not an explicit natural language description, but rather a machine learning model representation. Some embodiments additionally leverage a visual modality obtained from a vision-only model or branch, which may learn domain characteristics that are not present in the multi-modal network. Some embodiments additionally fuse or integrate the intrinsic modality with the visual modality for better generalization.

公开(公告)号：US20220012530A1

公开(公告)日：2022-01-13

申请号：US16926511

申请日：2020-07-10

Applicant: Adobe Inc.

Inventor： Mayank SINGH ,  Balaji Krishnamurthy ,  Nupur KUMARI ,  Puneet MANGLA

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06T7/11

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.