Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Apparatus and methods for image data classification

A technology of image data and equipment, applied in the field of target recognition, which can solve the problems of prediction without error correction ability and limited discriminative hidden features.

Active Publication Date: 2017-05-17
BEIJING SENSETIME TECH DEV CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the discriminative hidden features formed in the neural network system trained by 1-pair K encoding are limited, and the predictions generated by the neural network system do not have the ability of error correction

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
  • Apparatus and methods for image data classification
  • Apparatus and methods for image data classification
  • Apparatus and methods for image data classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] This section provides details of exemplary embodiments, examples of which are illustrated in the accompanying drawings. Wherever appropriate, the same reference numbers will be used throughout the drawings to refer to the same or like parts. figure 1 is a schematic diagram illustrating an exemplary apparatus 1000 for data classification consistent with some disclosed embodiments.

[0023] It should be appreciated that device 1000 may be implemented using some hardware, software, or a combination thereof. Furthermore, embodiments of the present application may be adapted for a computer program product embodied on one or more computer-readable storage media (including but not limited to, disk storage, CD-ROM, optical storage, etc.) that The medium contains computer program code.

[0024] Where device 1000 is implemented in software, device 1000 may run on one or more systems, which may include a general-purpose computer, a computer cluster, a mainstream computer, a comp...

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

Disclosed is an apparatus for image data classification. The apparatus may comprise: a target code generator configured to retrieve a plurality of training data samples and to generate a target code for each of the retrieved training data samples, wherein the training data samples being grouped into different classes, and the generated target code has a dimension identical to number of the classes; a target prediction generator configured to receive a plurality of arbitrary data samples and to generate a target prediction for each of the received arbitrary data samples; and a predictor configured to predict a class for each of the received arbitrary data sample based on the generated target code and the generated target prediction. A method for image data classification is also disclosed.

Description

technical field [0001] The present application relates generally to the field of object recognition, and more particularly, to apparatus and methods for classification of image data. Background technique [0002] Learning robust and invariant representations has been a long-standing goal of computer vision. Compared with hand-crafted visual features such as SIFT or HoG, it has recently been shown that features learned by deep models are better able to capture abstract concepts that are invariant under various phenomena of the visual world, e.g. viewpoint, lighting, and clutter. Therefore, more and more studies are exploring the use of deep representations for vision problems, especially for classification tasks. [0003] Instead of using deep models for direct classification, much vision research chooses to follow multi-stage techniques. This technique has been shown to be effective in combining the good invariant behavior of deep features with the discriminative power of ...

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): G06K9/66
CPCH04L1/0057G06N3/084G06V10/82G06V10/764G06N3/045
Inventor 汤晓鸥杨硕罗平吕健勤
Owner BEIJING SENSETIME TECH DEV CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com