中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

22 records (took 0.016 seconds)

    Object Detection In Images
    3.
    发明申请
    Object Detection In Images 有权

    公开(公告)号：US20220157054A1

    公开(公告)日：2022-05-19

    申请号：US17588516

    申请日：2022-01-31

    Applicant: Adobe Inc.

    Inventor： Zhe Lin ,  Xiaohui Shen ,  Mingyang Ling ,  Jianming Zhang ,  Jason Wen Yong Kuen

    IPC: G06V20/20 ,  G06K9/62 ,  G06N3/04 ,  G06V20/64

    Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.

    Multi-source panoptic feature pyramid network
    4.
    发明授权
    Multi-source panoptic feature pyramid network 有权

    公开(公告)号：US11941884B2

    公开(公告)日：2024-03-26

    申请号：US17454740

    申请日：2021-11-12

    Applicant: ADOBE INC.

    Inventor： Jason Wen Yong Kuen ,  Bo Sun ,  Zhe Lin ,  Simon Su Chen

    IPC: G06K9/00 ,  G06F18/21 ,  G06N3/08 ,  G06T9/00 ,  G06V10/75 ,  G06V20/40

    CPC classification number: G06V20/41 ,  G06F18/2163 ,  G06N3/08 ,  G06T3/4046 ,  G06T9/002 ,  G06V10/751

    Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image having a plurality of object instances; encode the image to obtain image features; decode the image features to obtain object features; generate object detection information based on the object features using an object detection branch, wherein the object detection branch is trained based on a first training set using a detection loss; generate semantic segmentation information based on the object features using a semantic segmentation branch, wherein the semantic segmentation branch is trained based on a second training set different from the first training set using a semantic segmentation loss; and combine the object detection information and the semantic segmentation information to obtain panoptic segmentation information that indicates which pixels of the image correspond to each of the plurality of object instances.

    MULTI-SOURCE PANOPTIC FEATURE PYRAMID NETWORK
    7.
    发明公开
    MULTI-SOURCE PANOPTIC FEATURE PYRAMID NETWORK 审中-公开

    公开(公告)号：US20230154185A1

    公开(公告)日：2023-05-18

    申请号：US17454740

    申请日：2021-11-12

    Applicant: ADOBE INC.

    Inventor： Jason Wen Yong Kuen ,  Bo Sun ,  Zhe Lin ,  Simon Su Chen

    IPC: G06K9/00 ,  G06K9/62 ,  G06T3/40 ,  G06T9/00 ,  G06N3/08

    CPC classification number: G06K9/00624 ,  G06K9/6202 ,  G06K9/6261 ,  G06N3/08 ,  G06T3/4046 ,  G06T9/002

    Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image having a plurality of object instances; encode the image to obtain image features; decode the image features to obtain object features; generate object detection information based on the object features using an object detection branch, wherein the object detection branch is trained based on a first training set using a detection loss; generate semantic segmentation information based on the object features using a semantic segmentation branch, wherein the semantic segmentation branch is trained based on a second training set different from the first training set using a semantic segmentation loss; and combine the object detection information and the semantic segmentation information to obtain panoptic segmentation information that indicates which pixels of the image correspond to each of the plurality of object instances.

    DETECTING DIGITAL OBJECTS AND GENERATING OBJECT MASKS ON DEVICE
    8.
    发明申请
    DETECTING DIGITAL OBJECTS AND GENERATING OBJECT MASKS ON DEVICE 有权

    公开(公告)号：US20230128792A1

    公开(公告)日：2023-04-27

    申请号：US17589114

    申请日：2022-01-31

    Applicant: Adobe Inc.

    Inventor： Jason Wen Yong Kuen ,  Su Chen ,  Scott Cohen ,  Zhe Lin ,  Zijun Wei ,  Jianming Zhang

    IPC: G06V10/82 ,  G06N3/08 ,  G06T7/00

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates object masks for digital objects portrayed in digital images utilizing a detection-masking neural network pipeline. In particular, in one or more embodiments, the disclosed systems utilize detection heads of a neural network to detect digital objects portrayed within a digital image. In some cases, each detection head is associated with one or more digital object classes that are not associated with the other detection heads. Further, in some cases, the detection heads implement multi-scale synchronized batch normalization to normalize feature maps across various feature levels. The disclosed systems further utilize a masking head of the neural network to generate one or more object masks for the detected digital objects. In some cases, the disclosed systems utilize post-processing techniques to filter out low-quality masks.

    Knowledge distillation for neural networks using multiple augmentation strategies
    9.
    发明授权
    Knowledge distillation for neural networks using multiple augmentation strategies 有权

    公开(公告)号：US11610393B2

    公开(公告)日：2023-03-21

    申请号：US17062157

    申请日：2020-10-02

    Applicant: Adobe Inc.

    Inventor： Jason Wen Yong Kuen ,  Zhe Lin ,  Jiuxiang Gu

    IPC: G06V10/778 ,  G06K9/62 ,  G06N3/04 ,  G06T3/60 ,  G06T3/40 ,  G06V10/774

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently learning parameters of a distilled neural network from parameters of a source neural network utilizing multiple augmentation strategies. For example, the disclosed systems can generate lightly augmented digital images and heavily augmented digital images. The disclosed systems can further learn parameters for a source neural network from the lightly augmented digital images. Moreover, the disclosed systems can learn parameters for a distilled neural network from the parameters learned for the source neural network. For example, the disclosed systems can compare classifications of heavily augmented digital images generated by the source neural network and the distilled neural network to transfer learned parameters from the source neural network to the distilled neural network via a knowledge distillation loss function.

    Object detection in images
    10.
    发明授权
    Object detection in images 有权

    公开(公告)号：US11256918B2

    公开(公告)日：2022-02-22

    申请号：US16874114

    申请日：2020-05-14

    Applicant: Adobe Inc.

    Inventor： Zhe Lin ,  Xiaohui Shen ,  Mingyang Ling ,  Jianming Zhang ,  Jason Wen Yong Kuen

    IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04

    Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.

Patent Agency Ranking