Saurabh Singh

20210335017, Oct 28, 2021

May 16, 2018

16/610063

- Mountain View CA, US
Damien Vincent - Zurich, CH
David Charles Minnen - Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Sung Jin Hwang - Mountain View CA, US
Nicholas Johnston - San Jose CA, US
Joel Eric Shor - Mountain View CA, US
George Dan Toderici - Mountain View CA, US

G06T 9/00

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.

20200364603, Nov 19, 2020

May 13, 2020

15/931016

- Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Johannes Balle - San Francisco CA, US
Abhinav Shrivastava - Silver Spring MD, US

G06N 20/00
G06N 3/08

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.

20200311548, Oct 1, 2020

Oct 29, 2019

16/666689

- Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Johannes Balle - San Francisco CA, US
Sami Ahmad Abu-El-Haija - East Palo Alto CA, US
Nicholas Johnston - San Jose CA, US
George Dan Toderici - Mountain View CA, US

G06N 3/08
G06N 3/063
G06K 9/62
G06F 17/15

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.

20200111238, Apr 9, 2020

May 29, 2018

16/617484

- Mountain View CA, US
Damien Vincent - Zurich, CH
David Charles Minnen - Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Sung Jin Hwang - Mountain View CA, US
Nicholas Johnston - San Jose CA, US
Joel Eric Shor - Mountain View CA, US
George Dan Toderici - Mountain View CA, US

G06T 9/00
G06T 3/40
G06T 7/00
G06N 3/04
G06N 3/08

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. An image encoder system receives a request to generate an encoded representation of an input image that has been partitioned into a plurality of tiles and generates the encoded representation of the input image. To generate the encoded representation, the system processes a context for each tile using a spatial context prediction neural network that has been trained to process context for an input tile and generate an output tile that is a prediction of the input tile. The system determines a residual image between the particular tile and the output tile generated by the spatial context prediction neural network by process the context for the particular tile and generates a set of binary codes for the particular tile by encoding the residual image using an encoder neural network.

20200027247, Jan 23, 2020

Jul 18, 2019

16/515586

- Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Johannes Balle - San Francisco CA, US
Troy Chinen - Newark CA, US
Sung Jin Hwang - Mountain View CA, US
Nicholas Johnston - San Jose CA, US
George Dan Toderici - Mountain View CA, US

G06T 9/00
G06T 3/40
G06N 3/08
G06N 20/00
G06F 17/18

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.

20190356330, Nov 21, 2019

May 21, 2018

15/985340

- Mountain View CA, US
Michele Covell - Woodside CA, US
Saurabh Singh - Mountain View CA, US
Sung Jin Hwang - Mountain View CA, US
George Dan Toderici - Mountain View CA, US

H03M 7/30
G06F 17/30
G06N 3/08
G06N 7/00
H04N 19/13
H04N 19/192

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, an encoder neural network processes data to generate an output including a representation of the data as an ordered collection of code symbols. The ordered collection of code symbols is entropy encoded using one or more code symbol probability distributions. A compressed representation of the data is determined based on the entropy encoded representation of the collection of code symbols and data indicating the code symbol probability distributions used to entropy encode the collection of code symbols. In another aspect, a compressed representation of the data is decoded to determine the collection of code symbols representing the data. A reconstruction of the data is determined by processing the collection of code symbols by a decoder neural network.