US 11,887,357 B2 · Adversarial network for transfer learning

Abstract

Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

Claims20

Dependent claims

A system comprising:

a processor;
and
memory coupled to the processor and storing instructions that, when executed by the processor, cause the system to perform operations comprising:
performing a deep correlation alignment to match a mean and covariance for a distribution of a first classification space with a distribution of a second classification space comprising a target domain;
generating, based at least in part on the target domain and a first media content item, a media overlay;
and
causing display, on a client device associated with the target domain, of a second media content item with the media overlay applied thereto.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application

17/547,548Filed 10 Dec 2021 · continuation

Priority

10 Oct 2017

Published

US 2022/0172003 A12 Jun 2022

Granted

30 Jan 2024

Term ends

Not estimatedThe source records don’t support an estimate.

Classification15 codes

G06V 10/7753
Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting: incorporation of unlabelled data, e.g. multiple instance…
G06F 18/2155
Generating training patterns; Bootstrap methods, e.g. bagging or boosting: characterised by the incorporation of unlabelled data, e.g. multiple…
G06F 18/217
Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation: validation; Performance…
G06F 18/24
Analysing: classification techniques

Family

Application62/570,531Us provisional application · filed 10 Oct 2017

Application16/156,882Parent of this continuation · filed 10 Oct 2018

US 2022/0172003 A1Pre-grant publication · published 2 Jun 2022

US 11,200,459 B1Parent of this continuation

US 11,887,357 B2This patent

From the US filing history. Foreign family members aren’t listed.

Adversarial network for transfer learning

Life of this patent

Adversarial network for transfer learning

Life of this patent

Abstract

Claims20