公开(公告)号：US20220084255A1

公开(公告)日：2022-03-17

申请号：US17021688

申请日：2020-09-15

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh

IPC: G06T9/00 ,  G06N3/08 ,  G06N3/04 ,  G06F17/18

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.

公开(公告)号：US11257254B2

公开(公告)日：2022-02-22

申请号：US16515586

申请日：2019-07-18

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh ,  Johannes Balle ,  Troy Chinen ,  Sung Jin Hwang ,  Nicholas Johnston ,  George Dan Toderici

IPC: G06T9/00 ,  G06N20/00 ,  G06F17/18 ,  G06N3/08 ,  G06T3/40

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.

公开(公告)号：US12026925B2

公开(公告)日：2024-07-02

申请号：US18461292

申请日：2023-09-05

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh

IPC: G06T9/00 ,  G06F17/18 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T9/002 ,  G06F17/18 ,  G06N3/045 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.

公开(公告)号：US11783511B2

公开(公告)日：2023-10-10

申请号：US18088283

申请日：2022-12-23

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh

IPC: G06T9/00 ,  G06F17/18 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06T9/002 ,  G06F17/18 ,  G06N3/045 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.

公开(公告)号：US20230206512A1

公开(公告)日：2023-06-29

申请号：US18088283

申请日：2022-12-23

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh

IPC: G06T9/00 ,  G06F17/18 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06T9/002 ,  G06F17/18 ,  G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.

公开(公告)号：US11354822B2

公开(公告)日：2022-06-07

申请号：US16610063

申请日：2018-05-16

Applicant: GOOGLE LLC

Inventor： Michele Covell ,  Damien Vincent ,  David Charles Minnen ,  Saurabh Singh ,  Sung Jin Hwang ,  Nicholas Johnston ,  Joel Eric Shor ,  George Dan Toderici

IPC: G06T9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. A request to generate an encoded representation of an input image is received. The encoded representation of the input image is then generated. The encoded representation includes a respective set of binary codes at each iteration. Generating the set of binary codes for the iteration from an initial set of binary includes: for any tiles that have already been masked off during any previous iteration, masking off the tile. For any tiles that have not yet been masked off during any of the previous iterations, a determination is made as to whether a reconstruction error of the tile when reconstructed from binary codes at the previous iterations satisfies an error threshold. When the reconstruction quality satisfies the error threshold, the tile is masked off.

公开(公告)号：US20220138991A1

公开(公告)日：2022-05-05

申请号：US17578794

申请日：2022-01-19

Applicant: Google LLC

Inventor： David Charles Minnen ,  Saurabh Singh ,  Johannes Balle ,  Troy Chinen ,  Sung Jin Hwang ,  Nicholas Johnston ,  George Dan Toderici

IPC: G06T9/00 ,  G06N20/00 ,  G06F17/18 ,  G06N3/08 ,  G06T3/40

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.

公开(公告)号：US20210335017A1

公开(公告)日：2021-10-28

申请号：US16610063

申请日：2018-05-16

Applicant: GOOGLE LLC

Inventor： Michele Covell ,  Damien Vincent ,  David Charles Minnen ,  Saurabh Singh ,  Sung Jin Hwang ,  Nicholas Johnston ,  Joel Eric Shor ,  George Dan Toderici

IPC: G06T9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. A request to generate an encoded representation of an input image is received. The encoded representation of the input image is then generated. The encoded representation includes a respective set of binary codes at each iteration. Generating the set of binary codes for the iteration from an initial set of binary includes: for any tiles that have already been masked off during any previous iteration, masking off the tile. For any tiles that have not yet been masked off during any of the previous iterations, a determination is made as to whether a reconstruction error of the tile when reconstructed from binary codes at the previous iterations satisfies an error threshold. When the reconstruction quality satisfies the error threshold, the tile is masked off.

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

IPC: G06N3/08 ,  G06N3/063 ,  G06K9/62 ,  G06F17/15

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：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

IPC: G06K9/00 ,  G06F17/15 ,  G06F18/24 ,  G06N3/063 ,  G06N3/08 ,  G06N3/082

CPC classification number: G06N3/08 ,  G06F17/15 ,  G06F18/24 ,  G06N3/063 ,  G06N3/082

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.