公开(公告)号：US12288393B2

公开(公告)日：2025-04-29

申请号：US17798969

申请日：2021-06-04

Applicant: Google LLC

Inventor： Rudy Bunel ,  Jim Huibrecht Winkens ,  Abhijit Guha Roy ,  Olaf Ronneberger ,  Seyed Mohammadali Eslami ,  Ali Taylan Cemgil ,  Simon Kohl

IPC: G06V10/82 ,  G06T7/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network to (i) generate accurate network outputs for a machine learning task and (ii) generate intermediate outputs that can be used to reliably classify out-of-distribution inputs. In one aspect, a method comprises: training the neural network using supervised and contrastive losses, comprising repeatedly performing operations including: obtaining first and second network inputs; processing each network input using the neural network to generate its respective network input embedding; processing the first network input using the neural network to generate a network output; and adjusting the network parameter values using supervised and contrastive loss gradients, wherein: the supervised loss is based on: (i) the network output, and (ii) a corresponding target network output; and the contrastive loss is based on at least: (i) the first network input embedding, and (ii) the second network input embedding.

公开(公告)号：US20250149171A1

公开(公告)日：2025-05-08

申请号：US18834165

申请日：2023-01-30

Applicant: Google LLC

Inventor： Jim Huibrecht Winkens ,  Alan Prasana Karthikesalingam ,  Krishnamurthy Dvijotham ,  Ali Taylan Cemgil ,  Sumedh Kedar Ghaisas

IPC: G16H50/20 ,  G06V10/764 ,  G16H30/20

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data points using a deferral model that determines whether to classify the data point using an output of one or more diagnostic machine learning models or to defer the data point for classification by one or more users.