公开(公告)号：US20220129670A1

公开(公告)日：2022-04-28

申请号：US17082479

申请日：2020-10-28

Applicant: ADOBE INC.

Inventor： ZHE LIN ,  LUIS FIGUEROA ,  ZHIHONG DING ,  SCOTT COHEN

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06T3/40 ,  G06N3/08

Abstract: A distractor detector includes a heatmap network and a distractor classifier. The heatmap network operates on an input image to generate a heatmap for a main subject, a heatmap for a distractor, and optionally a heatmap for the background. Each object is cropped within the input image to generate a corresponding cropped image. Regions within the heatmaps that correspond to the objects are identified, and each of the regions is cropped within each of the heatmaps to generate cropped heatmaps. The distractor classifier then operates on the cropped images and the cropped heatmaps to classify each of the objects as being either a main subject or a distractor.

公开(公告)号：US20200250465A1

公开(公告)日：2020-08-06

申请号：US16853111

申请日：2020-04-20

Applicant: Adobe Inc.

Inventor： ZHE LIN ,  XIAOHUI SHEN ,  JONATHAN BRANDT ,  JIANMING ZHANG ,  CHEN FANG

IPC: G06K9/62 ,  G06F16/51 ,  G06F16/28 ,  G06F16/2457 ,  G06K9/46 ,  G06F16/583 ,  G06N3/04 ,  G06N3/08

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

公开(公告)号：US20200334501A1

公开(公告)日：2020-10-22

申请号：US16388115

申请日：2019-04-18

Applicant: ADOBE INC

Inventor： ZHE LIN ,  MINGYANG LING ,  JIANMING ZHANG ,  JASON KUEN ,  FEDERICO PERAZZI ,  BRETT BUTTERFIELD ,  BALDO FAIETA

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/34

Abstract: Systems and methods are described for object detection within a digital image using a hierarchical softmax function. The method may include applying a first softmax function of a softmax hierarchy on a digital image based on a first set of object classes that are children of a root node of a class hierarchy, then apply a second (and subsequent) softmax functions to the digital image based on a second (and subsequent) set of object classes, where the second (and subsequent) object classes are children nodes of an object class from the first (or parent) object classes. The methods may then include generating an object recognition output using a convolutional neural network (CNN) based at least in part on applying the first and second (and subsequent) softmax functions. In some cases, the hierarchical softmax function is the loss function for the CNN.