公开(公告)号：US20230401827A1

公开(公告)日：2023-12-14

申请号：US17806097

申请日：2022-06-09

Applicant: ADOBE INC.

Inventor： Jason Wen Yong Kuen ,  Dat Ba Huynh ,  Zhe Lin ,  Jiuxiang Gu

IPC: G06V10/774 ,  G06V10/26 ,  G06V10/75 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V10/774 ,  G06V10/26 ,  G06V10/759 ,  G06V10/7715 ,  G06V10/776 ,  G06V10/82

Abstract: Systems and methods for image segmentation are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; compute noise information for the training image using a noise estimation network; and update parameters of the student network based on the mask, the pseudo mask, and the noise information.

公开(公告)号：US20230252774A1

公开(公告)日：2023-08-10

申请号：US17650437

申请日：2022-02-09

Applicant: ADOBE INC.

Inventor： Jason Wen Yong Kuen ,  Dat Ba Huynh ,  Zhe Lin ,  Jiuxiang Gu

IPC: G06V10/778 ,  G06V10/82 ,  G06V10/86 ,  G06V10/22 ,  G06V10/77 ,  G06V10/764 ,  G06V10/776 ,  G06T7/11 ,  G06T7/70

CPC classification number: G06V10/7792 ,  G06T7/11 ,  G06T7/70 ,  G06V10/22 ,  G06V10/82 ,  G06V10/86 ,  G06V10/764 ,  G06V10/776 ,  G06V10/7715 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; and update parameters of the student network based on the mask and the pseudo mask.