Processing method and device for image recognition model

A technology of image recognition and model processing, applied in the computer field, can solve problems such as errors, model robustness, loss, etc.

Active Publication Date: 2021-09-10
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the ImageNet C data set shows that image classifiers may have differences in identifying disturbed noise samples with rain, snow, fog, etc., resulting in robustness problems for image recognition models.
Model robustness issues may lead to safety issues or

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
  • Processing method and device for image recognition model
  • Processing method and device for image recognition model
  • Processing method and device for image recognition model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0026] figure 1 A schematic diagram of a specific implementation architecture for preprocessing an image recognition model in this specification is described. It is understandable that the image recognition model trained by using normal samples may make a wrong judgment on some abnormal samples, such as adversarial samples, samples added with disturbances such as light or fog in the physical world, in the process of recognizing targets. The situation where the model discriminates incorrectly is called a model hole. The purpose of the preprocessing scheme for the image recognition model provided in this manual is to automatically find out the loopholes in the model and repair them with an effective scheme. The implementation architecture can be realized by a computing platform. The computing platform here is, for example, any terminal, device, computer...

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 embodiment of the invention provides a processing method and device for an image recognition model. Through the method and device provided by the embodiment of the invention, for the image recognition model pre-trained by using a sample set, a first image under a relatively small first resolution is obtained based on a first sample image in the sample set, then, for the first image, a first adversarial sample image is generated by using a pre-trained image recognition model, and then the resolution of the first adversarial sample image is improved to obtain a second image under a larger second resolution, and the pre-trained image recognition model is further trained by using the second image and the first recognition tag corresponding to the first sample image as a first correction sample, so that the corrected image recognition model is used for image recognition. According to the embodiment, the model vulnerability is found through the low-resolution image, and the model vulnerability is repaired through the high-resolution image, so that the robustness of the image recognition model is improved.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular to a processing method and device for an image recognition model. Background technique [0002] With the development of machine learning technology, deep learning has made great breakthroughs in tasks such as image classification, image detection, and face recognition, and even in some tasks, the recognition ability of the model exceeds that of human beings. However, studies have shown that the recognition ability of cutting-edge classification models may be affected under the disturbance of perturbation. In other words, when there are distracting factors in the picture, the image recognition results of machine learning may be wrong. For example, the ImageNet C data set shows that image classifiers may have differences in identifying disturbed noise samples with rain, snow, fog and other weather, resulting in robustness problems for image recogn...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 翁海琴
Owner ALIPAY (HANGZHOU) INFORMATION 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