公开(公告)号：US11803971B2

公开(公告)日：2023-10-31

申请号：US17319979

申请日：2021-05-13

Applicant: Adobe Inc.

Inventor： Jaedong Hwang ,  Seoung Wug Oh ,  Joon-Young Lee

IPC: G06T7/11 ,  G06V10/40 ,  G06F18/2413

CPC classification number: G06T7/11 ,  G06F18/24137 ,  G06V10/40 ,  G06T2207/20084

Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.

公开(公告)号：US20220375090A1

公开(公告)日：2022-11-24

申请号：US17319979

申请日：2021-05-13

Applicant: Adobe Inc.

Inventor： Jaedong Hwang ,  Seoung Wug Oh ,  Joon-Young Lee

IPC: G06T7/11 ,  G06K9/62 ,  G06K9/46

Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.

公开(公告)号：US20240037750A1

公开(公告)日：2024-02-01

申请号：US18487453

申请日：2023-10-16

Applicant: Adobe Inc.

Inventor： Jaedong Hwang ,  Seoung Wug Oh ,  Joon-Young Lee

IPC: G06T7/11 ,  G06V10/40 ,  G06F18/2413

CPC classification number: G06T7/11 ,  G06V10/40 ,  G06F18/24137 ,  G06T2207/20084

Abstract: This disclosure describes one or more implementations of a panoptic segmentation system that generates panoptic segmented digital images that classify both known and unknown instances of digital images. For example, the panoptic segmentation system builds and utilizes a panoptic segmentation neural network to discover, cluster, and segment new unknown object subclasses for previously unknown object instances. In addition, the panoptic segmentation system can determine additional unknown object instances from additional digital images. Moreover, in some implementations, the panoptic segmentation system utilizes the newly generated unknown object subclasses to refine and tune the panoptic segmentation neural network to improve the detection of unknown object instances in input digital images.