公开(公告)号：US20250148752A1

公开(公告)日：2025-05-08

申请号：US18502719

申请日：2023-11-06

Applicant: QUALCOMM Incorporated

Inventor： Vibashan VISHNUKUMAR SHARMINI ,  Shubhankar Mangesh BORSE ,  Hyojin PARK ,  Debasmit DAS ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06V10/75 ,  G06V30/148

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. In an example method, an input image is accessed, and the input image is processed using an image encoder to generate an image embedding tensor. The image embedding tensor is processed using a mask decoder machine learning model to generate a set of mask embedding tensors. A textual input is processed using a text encoder to generate a text embedding tensor. A set of augmented masks is generated based on aggregating the text embedding tensor with the set of mask embedding tensors.