公开(公告)号：US20230015989A1

公开(公告)日：2023-01-19

申请号：US17365877

申请日：2021-07-01

Applicant: Nvidia Corporation

Inventor： Zhiding Yu ,  Rui Huang ,  Wonmin Byeon ,  Sifei Liu ,  Guilin Liu ,  Thomas Breuel ,  Anima Anandkumar ,  Jan Kautz

IPC: G06K9/46 ,  G06N3/04 ,  G06T7/13 ,  G06K9/62

Abstract: The disclosure provides a learning framework that unifies both semantic segmentation and semantic edge detection. A learnable recurrent message passing layer is disclosed where semantic edges are considered as explicitly learned gating signals to refine segmentation and improve dense prediction quality by finding compact structures for message paths. The disclosure includes a method for coupled segmentation and edge learning. In one example, the method includes: (1) receiving an input image, (2) generating, from the input image, a semantic feature map, an affinity map, and a semantic edge map from a single backbone network of a convolutional neural network (CNN), and (3) producing a refined semantic feature map by smoothing pixels of the semantic feature map using spatial propagation, and controlling the smoothing using both affinity values from the affinity map and edge values from the semantic edge map.

公开(公告)号：US20230177810A1

公开(公告)日：2023-06-08

申请号：US17853631

申请日：2022-06-29

Applicant: NVIDIA Corporation

Inventor： Jiarui Xu ,  Shalini De Mello ,  Sifei Liu ,  Wonmin Byeon ,  Thomas Breuel ,  Jan Kautz

IPC: G06V10/774 ,  G06V10/26

CPC classification number: G06V10/774 ,  G06V10/26

Abstract: Semantic segmentation includes the task of providing pixel-wise annotations for a provided image. To train a machine learning environment to perform semantic segmentation, image/caption pairs are retrieved from one or more databases. These image/caption pairs each include an image and associated textual caption. The image portion of each image/caption pair is passed to an image encoder of the machine learning environment that outputs potential pixel groupings (e.g., potential segments of pixels) within each image, while nouns are extracted from the caption portion and are converted to text prompts which are then passed to a text encoder that outputs a corresponding text representation. Contrastive loss operations are then performed on features extracted from these pixel groupings and text representations to determine an extracted feature for each noun of each caption that most closely matches the extracted features for the associated image.

公开(公告)号：US11790633B2

公开(公告)日：2023-10-17

申请号：US17365877

申请日：2021-07-01

Applicant: Nvidia Corporation

Inventor： Zhiding Yu ,  Rui Huang ,  Wonmin Byeon ,  Sifei Liu ,  Guilin Liu ,  Thomas Breuel ,  Anima Anandkumar ,  Jan Kautz

IPC: G06V10/50 ,  G06N3/04 ,  G06T7/13 ,  G06V10/75 ,  G06F18/2413

CPC classification number: G06V10/50 ,  G06F18/2413 ,  G06N3/04 ,  G06T7/13 ,  G06V10/758

Abstract: The disclosure provides a learning framework that unifies both semantic segmentation and semantic edge detection. A learnable recurrent message passing layer is disclosed where semantic edges are considered as explicitly learned gating signals to refine segmentation and improve dense prediction quality by finding compact structures for message paths. The disclosure includes a method for coupled segmentation and edge learning. In one example, the method includes: (1) receiving an input image, (2) generating, from the input image, a semantic feature map, an affinity map, and a semantic edge map from a single backbone network of a convolutional neural network (CNN), and (3) producing a refined semantic feature map by smoothing pixels of the semantic feature map using spatial propagation, and controlling the smoothing using both affinity values from the affinity map and edge values from the semantic edge map.