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：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.

公开(公告)号：US20220292356A1

公开(公告)日：2022-09-15

申请号：US17805405

申请日：2022-06-03

Applicant: ADOBE INC.

Inventor： Mayank SINGH ,  Abhishek SINHA ,  Balaji KRISHNAMURTHY

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N5/04 ,  G06F21/57

Abstract: Embodiments disclosed herein describe systems, methods, and products that generate trained neural networks that are robust against adversarial attacks. During a training phase, an illustrative computer may iteratively optimize a loss function that may include a penalty for ill-conditioned weight matrices in addition to a penalty for classification errors. Therefore, after the training phase, the trained neural network may include one or more well-conditioned weight matrices. The one or more well-conditioned weight matrices may minimize the effect of perturbations within an adversarial input thereby increasing the accuracy of classification of the adversarial input. By contrast, conventional training approaches may merely reduce the classification errors using backpropagation, and, as a result, any perturbation in an input is prone to generate a large effect on the output.