公开(公告)号：US20220254150A1

公开(公告)日：2022-08-11

申请号：US17485985

申请日：2021-09-27

Applicant: salesforce.com, inc.

Inventor： Cameron WOLFE ,  Keld LUNDGAARD

IPC: G06V10/80 ,  G06V10/776 ,  G06V30/194

Abstract: Methods, computer readable media, and devices for exceeding the limits of visual-linguistic multi-task learning are disclosed. One method may include identifying a multi-modal multi-task classification dataset including a plurality of data examples, creating a transformer machine learning model to predict a plurality of categorical attributes of a product, and training the transformer machine learning model based on the multi-modal multi-task classification dataset using an alpha decay schedule and dynamically allocating task-specific parameters for at least one of the plurality of task-specific classification heads based on task complexity.