公开(公告)号：US20240029413A1

公开(公告)日：2024-01-25

申请号：US18350845

申请日：2023-07-12

Applicant: Google LLC

Inventor： Anthony Jacob Piergiovanni ,  Weiching Kuo ,  Wei Li ,  Anelia Angelova

IPC: G06V10/774 ,  G06V10/25

CPC classification number: G06V10/774 ,  G06V10/25 ,  G06V2201/07

Abstract: A method involves the training of a model by dynamically adjusting the number of examples within each training batch. The dynamic adjustment is accomplished by adjusting the number of examples per task within each training batch according to the performance of the model on the tasks that the model is being trained on. In some embodiments, this method is applied to cross-modal vision-language tasks. This model may also be applied to the pre-training of a model that can be later fine-tuned for a more specific task(s).