公开(公告)号：US11756309B2

公开(公告)日：2023-09-12

申请号：US17148148

申请日：2021-01-13

Applicant: Waymo LLC

Inventor： Alper Ayvaci ,  Feiyu Chen ,  Justin Yu Zheng ,  Bayram Safa Cicek ,  Vasiliy Igorevich Karasev

IPC: G06N3/08 ,  G06V20/58 ,  B60W60/00

CPC classification number: G06V20/58 ,  B60W60/001 ,  G06N3/08 ,  B60W2420/52 ,  B60W2554/4049

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using contrastive learning. One of the methods includes obtaining a network input representing an environment; processing the network input using a first subnetwork of the neural network to generate a respective embedding for each location in the environment; processing the embeddings for each location in the environment using a second subnetwork of the neural network to generate a respective object prediction for each location; determining, for each of a plurality of pairs of the plurality of locations in the environment, whether the respective object predictions of the pair of locations characterize the same possible object or different possible objects; computing a respective contrastive loss value for each of the plurality of pairs of locations; and updating values for a plurality of parameters of the first subnetwork using the computed contrastive loss values.

公开(公告)号：US20220164585A1

公开(公告)日：2022-05-26

申请号：US17148148

申请日：2021-01-13

Applicant: Waymo LLC

Inventor： Alper Ayvaci ,  Feiyu Chen ,  Justin Yu Zheng ,  Bayram Safa Cicek ,  Vasiliy Igorevich Karasev

IPC: G06K9/00 ,  G06N3/08 ,  B60W60/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using contrastive learning. One of the methods includes obtaining a network input representing an environment; processing the network input using a first subnetwork of the neural network to generate a respective embedding for each location in the environment; processing the embeddings for each location in the environment using a second subnetwork of the neural network to generate a respective object prediction for each location; determining, for each of a plurality of pairs of the plurality of locations in the environment, whether the respective object predictions of the pair of locations characterize the same possible object or different possible objects; computing a respective contrastive loss value for each of the plurality of pairs of locations; and updating values for a plurality of parameters of the first subnetwork using the computed contrastive loss values.