Invention Application
- Patent Title: EXCEEDING THE LIMITS OF VISUAL-LINGUISTIC MULTI-TASK LEARNING
-
Application No.: US17485985Application Date: 2021-09-27
-
Publication No.: US20220254150A1Publication Date: 2022-08-11
- Inventor: Cameron WOLFE , Keld LUNDGAARD
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Main IPC: G06V10/80
- 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.
Public/Granted literature
- US11915471B2 Exceeding the limits of visual-linguistic multi-task learning Public/Granted day:2024-02-27
Information query