Adobe, Inc.

Google Inc.

Walmart Apollo, LLC

Waymo LLC

Wal-mart Stores, Inc.

Chenxi Liu

Zhe Lin

Xiaohui Shen

Jimei Yang

Xin Lu

Wei Shen

Zhao Zhao

Jianming Zhang

Dragomir Dimitrov Anguelov

Jen-Chan Jeff Chien

Jonathan J Huang

Yonghui Wu

Jonathon Shlens

Lu Wang

Barret Zoph

Wei Hua

Mingxing Tan

Kevin Patrick Murphy

Jia Li

Pei Sun

Jiahui Yu

Vahid Jalalibarsari

Fei-Fei Li

Weiyue Wang

Yuan Xie

Fei Xia

Zhaoqi Leng

Siyuan Qiao

Methods, systems, and apparatus for processing point clouds using neural networks to perform a machine learning task. In one aspect, a system comprises one or more computers configured to obtain a set of point clouds captured by one or more sensors. Each point cloud includes a respective plurality of three-dimensional points. The one or more computers assign the three-dimensional points to respective voxels in a voxel grid, where the grid of voxels includes non-empty voxels to which one or more points are assigned and empty voxels to which no points are assigned. For each non-empty voxel, the one or more computers generate initial features based on the points that are assigned to the non-empty voxel. The one or more computers generate multi-scale features of the voxel grid, and the one or more computers generate an output for a point cloud processing task using the multi-scale features of the voxel grid.

Performing point cloud tasks using multi-scale features generated through self-attention

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks through contrastive learning. In particular, the contrastive learning is modified to use a relative margin to adjust a training pair's contribution to optimization.

Relative margin for contrastive learning

A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.

Neural architecture search using a performance prediction neural network

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of obtaining a uniform resource locator (URL) of a first webpage that is shown on a graphical user interface and that is external to a website of a retailer (where, in some embodiments, the URL is obtained from a referral website or is entered by a user from a chat window or search box), using a web scraper to extract web text displayed on the first webpage on the graphical user interface, processing the web text displayed on the first webpage on the graphical user interface to determine an interest of a user, using a set of rules to determine items related to the web text displayed on the first webpage on the graphical user interface, and coordinating displaying the items on a second webpage to promote the items as related to the interest of the user, where the second webpage is internal or external to the website of the retailer.

Systems and methods for processing or mining visitor interests from graphical user interfaces displaying referral websites

Systems and methods including one or more processors and one or more non-transitory computer-readable media having computing instructions that are configured to run on the one or more processors and perform acts of receiving a test set comprising potential candidate items for substitution for a target item, determining association scores for each of the potential candidate items in the test set, determining one or more semantic similarity features of the potential candidate items in the test set, determining one or more image similarity features of the potential candidate items in the test set, and creating a substitutive probability model by determining a relative contribution of each of the association scores, the semantic similarity features and the image similarity features to a substitutive probability for the potential candidate items in the test set, with reference to a baseline set of the potential candidate items. Additional embodiments are disclosed herein.

Systems and methods for identifying candidates for item substitution

Systems, methods, and non-transitory computer-readable media are disclosed for segmenting objects in digital visual media utilizing one or more salient content neural networks. In particular, in one or more embodiments, the disclosed systems and methods train one or more salient content neural networks to efficiently identify foreground pixels in digital visual media. Moreover, in one or more embodiments, the disclosed systems and methods provide a trained salient content neural network to a mobile device, allowing the mobile device to directly select salient objects in digital visual media utilizing a trained neural network. Furthermore, in one or more embodiments, the disclosed systems and methods train and provide multiple salient content neural networks, such that mobile devices can identify objects in real-time digital visual media feeds (utilizing a first salient content neural network) and identify objects in static digital images (utilizing a second salient content neural network).

Deep salient content neural networks for efficient digital object segmentation

The invention is directed towards segmenting images based on natural language phrases. An image and an n-gram, including a sequence of tokens, are received. An encoding of image features and a sequence of token vectors are generated. A fully convolutional neural network identifies and encodes the image features. A word embedding model generates the token vectors. A recurrent neural network (RNN) iteratively updates a segmentation map based on combinations of the image feature encoding and the token vectors. The segmentation map identifies which pixels are included in an image region referenced by the n-gram. A segmented image is generated based on the segmentation map. The RNN may be a convolutional multimodal RNN. A separate RNN, such as a long short-term memory network, may iteratively update an encoding of semantic features based on the order of tokens. The first RNN may update the segmentation map based on the semantic feature encoding.

Automatically segmenting images based on natural language phrases

Growing community of inventors

Santa Clara, CA, United States of America

Chenxi Liu