-
公开(公告)号：US20210124993A1
公开(公告)日：2021-04-29
申请号：US16661617
申请日：2019-10-23
Applicant: Adobe Inc.
Inventor： Mayank Singh , Puneet Mangla , Nupur Kumari , Balaji Krishnamurthy , Abhishek Sinha
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
-
Patent Agency Ranking
公开(公告)号：US11875512B2
公开(公告)日：2024-01-16
申请号：US18148256
申请日：2022-12-29
Applicant: Adobe Inc.
Inventor： Mayank Singh , Balaji Krishnamurthy , Nupur Kumari , Puneet Mangla
IPC: G06T7/00 , G06T7/11 , G06N3/08 , G06N3/04 , G06F18/214 , G06F18/21 , G06V10/774 , G06V10/82
CPC classification number: G06T7/11 , G06F18/214 , G06F18/217 , G06N3/04 , G06N3/08 , G06V10/774 , G06V10/82 , G06T2207/20081 , G06T2207/20084
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：US20240242394A1
公开(公告)日：2024-07-18
申请号：US18097856
申请日：2023-01-17
Applicant: Adobe Inc.
Inventor： Puneet Mangla , Balaji Krishnamurthy
IPC: G06T11/00 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
CPC classification number: G06T11/00 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
Abstract: In implementations of systems for non-adversarial image generation using transfer learning, a computing device implements a generation system to receive input data describing random noise. The generation system generates a latent representation in a latent space of a machine learning model based on the random noise using a transformer model that is trained to generate latent representations in the latent space. A digital image is generated using the machine learning model based on the latent representation that depicts an object that is visually similar to objects depicted in digital images of a training dataset used to train the machine learning model based on a perceptual loss.
-
公开(公告)号：US11886803B1
公开(公告)日：2024-01-30
申请号：US18153595
申请日：2023-01-12
Applicant: Adobe Inc.
Inventor： Arneh Jain , Salil Taneja , Puneet Mangla , Gaurav Ahuja
IPC: G06F17/00 , G06F40/174 , G06F40/40
CPC classification number: G06F40/174 , G06F40/40
Abstract: In implementations of systems for assistive digital form authoring, a computing device implements an authoring system to receive input data describing a search input associated with a digital form. The authoring system generates an input embedding vector that represents the search input in a latent space using a machine learning model trained on training data to generate embedding vectors in the latent space. A candidate embedding vector included in a group of candidate embedding vectors is identified based on a distance between the input embedding vector and the candidate embedding vector in the latent space. The authoring system generates an indication of a search output associated with the digital form for display in a user interface based on the candidate embedding vector.
-
公开(公告)号：US11544495B2
公开(公告)日：2023-01-03
申请号：US16926511
申请日：2020-07-10
Applicant: Adobe Inc.
Inventor： Mayank Singh , Balaji Krishnamurthy , Nupur Kumari , Puneet Mangla
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：US11308353B2
公开(公告)日：2022-04-19
申请号：US16661617
申请日：2019-10-23
Applicant: Adobe Inc.
Inventor： Mayank Singh , Puneet Mangla , Nupur Kumari , Balaji Krishnamurthy , Abhishek Sinha
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
