Feedback
Settings

Settings

Goto Application

1. WO2022011233 - DATASET-AWARE AND INVARIANT LEARNING FOR FACE RECOGNITION

Submit observation
PermaLink
Publication Number WO/2022/011233
Publication Date 13.01.2022
International Application No. PCT/US2021/041047
International Filing Date 09.07.2021
IPC
G06N 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06K 9/00 2022.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/46 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06K 9/62 2022.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
G06K 9/64 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
64using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix
G06K 9/68 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
68using sequential comparisons of the image signals with a plurality of reference, e.g. addressable memory
CPC
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/0472
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0472using probabilistic elements, e.g. p-rams, stochastic processors
G06N 3/082
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
082modifying the architecture, e.g. adding or deleting nodes or connections, pruning
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
Applicants
  • WYZE LABS, INC. [US]/[US]
Inventors
  • CHEN, Lin
  • WANG, Gaoang
  • LIU, Tianqiang
Agents
  • PETTIT, Andrew T.
  • DUNHAM, Nicole S.
Priority Data
63/049,98709.07.2020US
63/143,48329.01.2021US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) DATASET-AWARE AND INVARIANT LEARNING FOR FACE RECOGNITION
(FR) APPRENTISSAGE INVARIANT ET COMPATIBLE AVEC DES JEUX DE DONNÉES POUR RECONNAISSANCE FACIALE
front page image
Abstract
(EN) Introduced here is an approach to training a model to perform facial recognition with a designed dataset-aware loss. This approach is particularly useful for large-scale, multi-dataset training since there are no prerequisites for label cleaning. Dataset-aware loss may be built upon the softmax function with a binary dataset indicator. Such an approach allows the dataset-aware loss to be readily combined with other losses to improve performance.
(FR) Est introduite ici une approche pour entraîner un modèle à effectuer une reconnaissance faciale avec une perte conçue comme compatible avec un jeu de données. Cette approche est particulièrement utile pour l'apprentissage à grande échelle et à multiples jeux de données puisqu'il n'existe aucun prérequis pour le nettoyage d'étiquettes. Une perte compatible avec un jeu de données peut être construite sur la fonction softmax avec un indicateur de jeu de données binaire. Une telle approche permet de combiner facilement la perte compatible avec un jeux de données avec d'autres pertes pour améliorer les performances.
Latest bibliographic data on file with the International Bureau
# -