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

Method and device for optimizing target detection framework, storage medium, and electronic equipment

A technology of target detection and optimization method, applied in the computer field, can solve the problems of unfavorable large-scale popularization, the training performance cannot reach FasterR-CNN, the target detection framework training speed is slow, etc., to achieve the effect of speeding up the training process and speeding up the matching speed.

Active Publication Date: 2021-02-05
BEIJING LLVISION TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the slow training speed of the target detection framework, the training performance of the target detection framework on the dataset cannot reach the Faster R-CNN (Region-convolutional neural network), which is not conducive to large-scale popularization in engineering practice

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 device for optimizing target detection framework, storage medium, and electronic equipment
  • Method and device for optimizing target detection framework, storage medium, and electronic equipment
  • Method and device for optimizing target detection framework, storage medium, and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details being omitted, or other methods, components, devices, steps, etc. may be adopted. In other instances, well-known technical solution...

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 disclosure belongs to the field of computer technology, and relates to an optimization method and device, a storage medium, and electronic equipment for a target detection framework. The method includes: obtaining multiple original embedding vectors and multiple annotation vectors corresponding to the target detection framework, and expanding the original embedding vectors to obtain multiple embedding vectors; calculating multiple embedding vectors to obtain a target cost matrix; Matrix, use the local optimal solution algorithm to match multiple embedding vectors and multiple label vectors to obtain multiple sets of matching vectors; calculate multiple sets of matching vectors to obtain the target loss function, and use the target loss function to train the target detection framework to use the optimized object detection framework for object detection or panoptic segmentation. The disclosure expands the number of matching vectors, solves the problem of few training samples of the target detection framework, speeds up the training process of the learning rate, speeds up the matching speed of embedding vectors and labeling vectors, and solves the problem of slow training speed.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a method for optimizing a target detection framework, an optimization device for a target detection framework, a computer-readable storage medium, and electronic equipment. Background technique [0002] The target detection framework can introduce the Transformer structure into the field of target detection. In the target detection framework, the Hungarian algorithm is used to match object queries and ground truths, so that the loss caused by matching is minimal. Since the object queries matching the ground truths are used as training positive samples, an object query can generate a positive sample, and the part of the object query set that does not match the ground truths is used as a training negative sample. [0003] However, due to the slow training speed of the target detection framework, the training performance of the target detection framework on the datas...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/047G06N3/045G06F18/2415G06F18/241
Inventor 姚寒星王锦申
Owner BEIJING LLVISION TECH CO LTD