公开(公告)号：US20240296337A1

公开(公告)日：2024-09-05

申请号：US18178225

申请日：2023-03-03

Applicant: ADOBE INC.

Inventor： Surgan Jandial ,  Tarun Ram Menta ,  Akash Sunil Patil ,  Chirag Agarwal ,  Mausoom Sarkar ,  Balaji Krishnamurthy

IPC: G06N3/096

CPC classification number: G06N3/096

Abstract: Systems and methods for transfer learning are provided. According to one aspect, a method for transfer learning includes obtaining a target dataset, a source dataset, and a machine learning model trained on the source dataset; selecting a hard subset of the target dataset based on a similarity between the hard subset and the source dataset; computing a transferability metric for the target dataset based on the hard subset of the target dataset; and training the machine learning model using the target dataset based on the transferability metric.

公开(公告)号：US20240403651A1

公开(公告)日：2024-12-05

申请号：US18328174

申请日：2023-06-02

Applicant: Adobe Inc.

Inventor： Shripad Vilasrao Deshmukh ,  Arpan Dasgupta ,  Balaji Krishnamurthy ,  Chirag Agarwal ,  Georgios Theocharous ,  Jayakumar Subramanian

IPC: G06N3/092

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that provide a trajectory-based explainability framework for reinforcement learning models. For example, the disclosed systems generate trajectory clusters from trajectories utilized to train a reinforcement learning agent. In some embodiments, the disclosed system generates a complementary target data set by removing a target trajectory cluster from the trajectory clusters. In some cases, the disclosed system trains a test reinforcement learning agent utilizing the complementary target data set and generates a cluster attribution by comparing the result of the test reinforcement learning agent with the result of the reinforcement learning agent.

公开(公告)号：US20240395024A1

公开(公告)日：2024-11-28

申请号：US18322253

申请日：2023-05-23

Applicant: Adobe Inc.

Inventor： Mayur Hemani ,  Chirag Agarwal ,  Ashish Seth

IPC: G06V10/776 ,  G06F16/33 ,  G06F40/40 ,  G06V10/74 ,  G06V10/764 ,  G06V10/77 ,  G06V10/82

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for debiasing vision-language models utilizing additive residual learning. In particular, in one or more embodiments, the disclosed systems generate an encoded image representation of a digital image utilizing an image encoder of a vision-language neural network. Additionally, in some embodiments, the disclosed systems extract a protected attribute encoding from the encoded image representation of the digital image utilizing an additive residual learner. Upon extracting the protected attribute encoding, in some implementations, the disclosed systems determine a debiased image encoding for the digital image by combining the protected attribute encoding and the encoded image representation.