Neural network optimization method and device and target detection method and device

A neural network and target detection technology, applied in neural learning methods, biological neural network models, etc., can solve problems such as poor neural network performance

Active Publication Date: 2019-11-12
SHANGHAI SENSETIME INTELLIGENT TECH CO LTD
View PDF14 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The performance of the neural network

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
  • Neural network optimization method and device and target detection method and device
  • Neural network optimization method and device and target detection method and device
  • Neural network optimization method and device and target detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the drawings. The same reference signs in the drawings indicate elements with the same or similar functions. Although various aspects of the embodiments are shown in the drawings, unless otherwise noted, the drawings are not necessarily drawn to scale.

[0061] The dedicated word "exemplary" here means "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" need not be construed as being superior or better than other embodiments.

[0062] The term "and / or" in this text is only an association relationship that describes the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean: A alone exists, A and B exist at the same time, exist alone B these three situations. In addition, the term "at least one" herein means any one of a plurality of or any ...

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

The invention relates to a neural network optimization method and device, and a target detection method and apparatus. The neural network optimization method comprises the steps of obtaining positioninformation of a plurality of candidate boxes of a target object of a target type in a first image; according to the first image, the position information of the plurality of candidate boxes and a neural network, obtaining image features of image regions corresponding to the plurality of candidate boxes in the first image, and a prediction result of the target object in the candidate boxes relatedto the target type; screening out at least two target candidate boxes satisfying a similarity condition from the plurality of candidate boxes based on the image features and the prediction results respectively corresponding to the plurality of candidate boxes; and optimizing the neural network based on the prediction results respectively corresponding to the at least two screened target candidateboxes. According to the embodiment of the invention, the target detection performance of the neural network can be improved.

Description

Technical field [0001] The present disclosure relates to the field of machine learning technology, in particular to a neural network optimization method and device, and target detection method and device. Background technique [0002] Target detection is an important issue in the field of computer vision. Target detection based on deep learning has been applied to many fields such as robot navigation, intelligent video surveillance, unmanned driving, industrial inspection, aerospace and so on. However, the training target detection (strongly supervised target detection) model requires a lot of manual labeling of target detection frames, which restricts the wider application of target detection technology to a certain extent. In response to this problem, some researchers have proposed a method of weakly supervised target detection. This method uses only image tags and combines the detection of the target detection frame with the highest confidence in the image to achieve network m...

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
IPC IPC(8): G06N3/08
CPCG06N3/082
Inventor 蔺琛皓许东奇卢宇王思雯张伟
Owner SHANGHAI SENSETIME INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap