Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and apparatus for zero-shot learning

A technology for testing samples and visual features, applied in the field of information processing, can solve the problems of not reflecting the internal structure of the semantic space, unsatisfactory performance, etc.

Inactive Publication Date: 2019-04-16
NOKIA TECHNOLOGLES OY
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional methods for ZSL cannot reflect the intrinsic structure in the semantic space, leading to unsatisfactory performance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and apparatus for zero-shot learning
  • Method and apparatus for zero-shot learning
  • Method and apparatus for zero-shot learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The principles of the disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described for the purpose of illustration only, and to help those skilled in the art to understand and implement the present disclosure, without implying any limitation on the scope of the present invention. The invention described herein can be implemented in various ways other than those described below.

[0025] As used herein, the term "includes" and variations thereof will be understood as an open term meaning "including but not limited to". The term "based on" should be understood as "based on at least". The terms "one embodiment" and "an embodiment" should be read as "at least one embodiment." The term "another embodiment" should be understood as "at least one other embodiment". Other explicit and implied definitions may be included below.

[0026] In general, embodiments of the present disclosure utilize the id...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Embodiments of the present disclosure provide a method, apparatus and computer program product for ZSL. The method comprises: constructing a dictionary model based on visual features and semantic features of multimedia content of seen classes, the semantic features corresponding to the visual features; reconstructing visual features of multimedia content of unseen classes using the dictionary model and semantic features of multimedia content of unseen classes; and determining a class of a testing sample based on comparison of a visual feature of the testing sample and reconstructed visual features.

Description

technical field [0001] Embodiments of the present disclosure relate generally to information processing, and more particularly to methods, apparatuses and computer program products for Zero-Shot Learning (ZSL). Background technique [0002] ZSL refers to a learning process where no training samples are available to distinguish new categories (also known as unseen categories). It aims to improve the scalability of traditional classification methods. It often arises in practice because of the large number of real-world object categories that are still changing. Obtaining human-annotated labels for each category would be too time-consuming and expensive. [0003] ZSL can be widely used in applications such as natural scene understanding, object recognition, autonomous vehicles, virtual reality, etc. For example, in the application of self-driving vehicles, it is necessary to recognize the surrounding objects. Traditional recognition methods need to pre-define some categorie...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/66G06K9/62G06K9/46
CPCG06V20/20G06V20/56G06F18/2135G06F18/28G06F18/2413G06F18/24147
Inventor 于云龙
Owner NOKIA TECHNOLOGLES OY