Qualcomm incorporated (20250148752). OPEN VOCABULARY IMAGE SEGMENTATION
OPEN VOCABULARY IMAGE SEGMENTATION
Organization Name
Inventor(s)
Vibashan Vishnukumar Sharmini of San Diego CA US
Shubhankar Mangesh Borse of San Diego CA US
Hyojin Park of San Diego CA US
Debasmit Das of San Diego CA US
Munawar Hayat of San Diego CA US
Fatih Murat Porikli of San Diego CA US
OPEN VOCABULARY IMAGE SEGMENTATION
This abstract first appeared for US patent application 20250148752 titled 'OPEN VOCABULARY IMAGE SEGMENTATION
Original Abstract Submitted
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.