-
公开(公告)号：US20180189935A1
公开(公告)日：2018-07-05
申请号：US15849379
申请日：2017-12-20
Applicant: Facebook, Inc.
Inventor： Jason George McHugh , Michael F. Cohen , Johannes Peter Kopf , Piotr Dollar
CPC classification number: G06T5/002 , G06N20/00 , G06T5/20 , G06T7/11 , G06T7/13 , G06T7/143 , G06T7/194 , G06T2207/20081 , G06T2207/20084 , G06T2207/20192
Abstract: Systems, methods, and non-transitory computer-readable media can generate an initial alpha mask for an image based on machine learning techniques. A plurality of uncertain pixels is defined in the initial alpha mask. For each uncertain pixel in the plurality of uncertain pixels, a binary value is assigned based on a nearest certain neighbor determination.
-
公开(公告)号：US11023772B2
公开(公告)日：2021-06-01
申请号：US16590256
申请日：2019-10-01
Applicant: Facebook, Inc.
Abstract: In one embodiment, a feature map of an image having h×w pixels and a patch having one or more pixels of the image are received. The patch has been processed by a first set of layers of a convolutional neural network and contains an object centered within the patch. The patch is then processed using the feature map and one or more pixel classifiers of a classification layer of a deep-learning model, where the classification layer includes h×w pixel classifiers, with each pixel classifier corresponding to a respective pixel of the patch. Each of the pixel classifiers used to process the patch outputs a respective value indicating whether the corresponding pixel belongs to the object centered in the patch.
-
公开(公告)号：US10255522B2
公开(公告)日：2019-04-09
申请号：US15624643
申请日：2017-06-15
Applicant: Facebook, Inc.
Abstract: In one embodiment, a plurality of patches of an image are processed using a first deep-learning model to detect a plurality of features associated with the first patch of the image. Each patch includes one or more pixels of the image. Using a second deep-learning model, a respective object proposal is generated for each of the plurality of patches of the image. The second deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and each object proposal includes a prediction as to a location of an object in the patch. Using a third deep-learning model, a respective score is computed for each object proposal generated using the second deep-learning model. The third deep-learning model takes as input the plurality of detected features associated with the respective patch of the image, and the object score may include a likelihood that the patch contains an entire object.
-
公开(公告)号：US20180285686A1
公开(公告)日：2018-10-04
申请号：US15853290
申请日：2017-12-22
Applicant: Facebook, Inc.
Abstract: In one embodiment a plurality of patches of an image are processed, using a first set of layers of a convolutional neural network, to output a plurality of object proposals associated with the plurality of patches of the image. Each patch includes one or more pixels of the image. Each object proposal includes a prediction as to a location of an object in the respective patch. Using a second set of layers of the convolutional neural network, the plurality of object proposals outputted by the first set of layers are processed to generate a plurality of refined object proposals. Each refined object proposal includes pixel-level information for the respective patch of the image. The first layer in the second set of layers of the convolutional neural network takes as input the plurality of object proposals outputted by the first set of layers. Each layer after the first layer in the second set of layers takes as input the output of a preceding layer in the second set of layers combined with the output of a respective layer of the first set of layers.
-
Patent Agency Ranking
公开(公告)号：US10713794B1
公开(公告)日：2020-07-14
申请号：US15922734
申请日：2018-03-15
Applicant: Facebook, Inc.
Inventor： Kaiming He , Georgia Gkioxari , Piotr Dollar , Ross Girshick
Abstract: In one embodiment, a method includes a computing system accessing a training image. The system may generate a feature map for the training image using a first neural network. The system may identify a region of interest in the feature map and generate a regional feature map for the region of interest based on sampling locations defined by a sampling region. The sampling region and the region of interest may correspond to the same region in the feature map. The system may generate an instance segmentation mask associated with the region of interest by processing the regional feature map using a second neural network. The second neural network may be trained using the instance segmentation mask. Once trained, the second neural network is configured to generate instance segmentation masks for object instances depicted in images.
-
公开(公告)号：US20200034653A1
公开(公告)日：2020-01-30
申请号：US16590256
申请日：2019-10-01
Applicant: Facebook, Inc.
Abstract: In one embodiment, a feature map of an image having h×w pixels and a patch having one or more pixels of the image are received. The patch has been processed by a first set of layers of a convolutional neural network and contains an object centered within the patch. The patch is then processed using the feature map and one or more pixel classifiers of a classification layer of a deep-learning model, where the classification layer includes h×w pixel classifiers, with each pixel classifier corresponding to a respective pixel of the patch. Each of the pixel classifiers used to process the patch outputs a respective value indicating whether the corresponding pixel belongs to the object centered in the patch.
-
公开(公告)号：US10607318B2
公开(公告)日：2020-03-31
申请号：US15849379
申请日：2017-12-20
Applicant: Facebook, Inc.
Inventor： Jason George McHugh , Michael F. Cohen , Johannes Peter Kopf , Piotr Dollar
Abstract: Systems, methods, and non-transitory computer-readable media can generate an initial alpha mask for an image based on machine learning techniques. A plurality of uncertain pixels is defined in the initial alpha mask. For each uncertain pixel in the plurality of uncertain pixels, a binary value is assigned based on a nearest certain neighbor determination.
-
公开(公告)号：US20190228259A1
公开(公告)日：2019-07-25
申请号：US16370491
申请日：2019-03-29
Applicant: Facebook, Inc.
Abstract: In one embodiment, a plurality of patches of an image are processed using a first-pass of a first deep-learning model to generate object-level information for each of the patches. Each patch includes one or more pixels of the image. Using a second-pass of the first deep-learning model, a respective object proposal is generated for each of the plurality of patches of the image. The second-pass takes as input the first-pass output, and the generated respective object proposals comprise pixel-level information for each of the patches. Using a second deep-learning model, a respective score is computed for each object proposal. The second deep-learning model takes as input the first-pass output, and the object score includes a likelihood that the respective patch of the object proposal contains an entire object.
-
公开(公告)号：US20170132510A1
公开(公告)日：2017-05-11
申请号：US14981413
申请日：2015-12-28
Applicant: Facebook, Inc.
Inventor： Balmanohar Paluri , Oren Rippel , Piotr Dollar , Lubomir Dimitrov Bourdev
CPC classification number: G06N3/08 , G06N3/0454 , H04L67/10 , H04L67/1097
Abstract: In one embodiment, a method may include receiving a first content item. A first embedding of the first content item may be determined and may corresponds to a first point in an embedding space. The embedding space may include a plurality of second points corresponding to a plurality of second embeddings of second content items. The embeddings are determined using a deep-learning model. The points are located in one or more clusters in the embedding space, which are each associated with a class of content items. Locations of points within clusters may be based on one or more attributes of the respective corresponding content items. Second content items that are similar to the first content item may be identified based on the locations of the first point and the second points and on particular clusters that the second points corresponding to the identified second content items are located in.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.014 seconds)
