-
公开(公告)号:US20200311548A1
公开(公告)日:2020-10-01
申请号:US16666689
申请日:2019-10-29
Applicant: Google LLC
Inventor: Abhinav Shrivastava , Saurabh Singh , Johannes Balle , Sami Ahmad Abu-El-Haija , Nicholas Johnston , George Dan Toderici
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.
-
公开(公告)号:US12265898B2
公开(公告)日:2025-04-01
申请号:US18409520
申请日:2024-01-10
Applicant: Google LLC
Inventor: Deniz Oktay , Saurabh Singh , Johannes Balle , Abhinav Shrivastava
Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.
-
公开(公告)号:US20210166009A1
公开(公告)日:2021-06-03
申请号:US16637960
申请日:2019-08-06
Applicant: Google LLC
Inventor: Chen Sun , Abhinav Shrivastava , Cordelia Luise Schmid , Rahul Sukthankar , Kevin Patrick Murphy , Carl Martin Vondrick
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing action localization. In one aspect, a system comprises a data processing apparatus; a memory in data communication with the data processing apparatus and storing instructions that cause the data processing apparatus to perform operations comprising: receiving an input comprising an image depicting a person; identifying a plurality of context positions from the image; determining respective feature representations of each of the context positions; providing a feature representation of the person and the feature representations of each of the context positions to a context neural network to obtain relational features, wherein the relational features represent relationships between the person and the context positions; and determining an action performed by the person using the feature representation of the person and the relational features.
-
公开(公告)号:US20210089777A1
公开(公告)日:2021-03-25
申请号:US16966102
申请日:2019-06-12
Applicant: Google LLC
Inventor: Abhinav Shrivastava , Alireza Fathi , Sergio Guadarrama Cotado , Kevin Patrick Murphy , Carl Martin Vondrick
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing visual tracking. In one aspect, a method comprises receiving: (i) one or more reference video frames, (ii) respective reference labels for each of a plurality of reference pixels in the reference video frames, and (iii) a target video frame. The reference video frames and the target video frame are processed using a colorization machine learning model to generate respective pixel similarity measures between each of (i) a plurality of target pixels in the target video frame, and (ii) the reference pixels in the reference video frames. A respective target label is determined for each target pixel in the target video frame, comprising: combining (i) the reference labels for the reference pixels in the reference video frames, and (ii) the pixel similarity measures.
-
公开(公告)号:US12033077B2
公开(公告)日:2024-07-09
申请号:US18175125
申请日:2023-02-27
Applicant: GOOGLE LLC
Inventor: Abhinav Shrivastava , Saurabh Singh , Johannes Ballé , Sami Ahmad Abu-El-Haija , Nicholas Milo Johnston , George Dan Toderici
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.
-
公开(公告)号:US11574232B2
公开(公告)日:2023-02-07
申请号:US15931016
申请日:2020-05-13
Applicant: Google LLC
Inventor: Deniz Oktay , Saurabh Singh , Johannes Balle , Abhinav Shrivastava
Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.
-
公开(公告)号:US20240220863A1
公开(公告)日:2024-07-04
申请号:US18409520
申请日:2024-01-10
Applicant: Google LLC
Inventor: Deniz Oktay , Saurabh Singh , Johannes Balle , Abhinav Shrivastava
Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.
-
公开(公告)号:US11610124B2
公开(公告)日:2023-03-21
申请号:US16666689
申请日:2019-10-29
Applicant: Google LLC
Inventor: Abhinav Shrivastava , Saurabh Singh , Johannes Balle , Sami Ahmad Abu-El-Haija , Nicholas Johnston , George Dan Toderici
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.
-
公开(公告)号:US20230237332A1
公开(公告)日:2023-07-27
申请号:US18175125
申请日:2023-02-27
Applicant: GOOGLE LLC
Inventor: Abhinav Shrivastava , Saurabh Singh , Johannes Ballé , Sami Ahmad Abu-El-Haija , Nicholas Milo Johnston , George Dan Toderici
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.
-
公开(公告)号:US11335093B2
公开(公告)日:2022-05-17
申请号:US16966102
申请日:2019-06-12
Applicant: Google LLC
Inventor: Abhinav Shrivastava , Alireza Fathi , Sergio Guadarrama Cotado , Kevin Patrick Murphy , Carl Martin Vondrick
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing visual tracking. In one aspect, a method comprises receiving: (i) one or more reference video frames, (ii) respective reference labels for each of a plurality of reference pixels in the reference video frames, and (iii) a target video frame. The reference video frames and the target video frame are processed using a colorization machine learning model to generate respective pixel similarity measures between each of (i) a plurality of target pixels in the target video frame, and (ii) the reference pixels in the reference video frames. A respective target label is determined for each target pixel in the target video frame, comprising: combining (i) the reference labels for the reference pixels in the reference video frames, and (ii) the pixel similarity measures.
-
-
-
-
-
-
-
-
-