Multi-model knowledge distillation method and device, electronic equipment and storage medium

A distillation method and multi-model technology, applied in the field of machine learning, can solve the problems of long consumption, high occupation and low efficiency, and achieve the effect of overcoming limited expression ability and improving model accuracy.

Active Publication Date: 2020-02-25
BEIJING SENSETIME TECH DEV CO LTD
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for larger neural networks, both in the training phase and the actual use phase, it takes a long time and takes up more resources.
For example, a larger neural network takes a long time to complete in the early stage of feature extraction, and the efficiency is low.

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
  • Multi-model knowledge distillation method and device, electronic equipment and storage medium
  • Multi-model knowledge distillation method and device, electronic equipment and storage medium
  • Multi-model knowledge distillation method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

[0051] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

[0052] The term "and / or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the term "at least one" herein mean...

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 multi-model knowledge distillation method and device, electronic equipment and a storage medium. The method comprises the steps of extracting features of a training image toobtain training data; inputting the training data into a plurality of sub-models included in a teacher model for operation, and obtaining a first feature output by the teacher model according to sub-features output by the plurality of sub-models; inputting the training data into a student model for operation to obtain a second feature output by the student model; determining a loss function of the student model according to the first feature and the second feature; and performing back propagation on the student model according to the loss function. According to the embodiment of the invention, different feature representations in the training data can be obtained by utilizing the plurality of sub-models in the teacher model, and the student model can learn features in the teacher model byutilizing a knowledge distillation mode, so that the problem of limited expression capability of a single model is solved, and the model precision of the student model is improved.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning, and in particular to a multi-model knowledge distillation method and device, electronic equipment and a storage medium. Background technique [0002] In the field of machine learning techniques, larger neural networks are required to perform complex tasks. However, a larger neural network takes a long time and takes up more resources in both the training phase and the actual use phase. For example, a larger neural network takes a long time to complete in the early stage of feature extraction, and the efficiency is low. Contents of the invention [0003] The present disclosure proposes a multi-model knowledge distillation technical solution. [0004] According to an aspect of the present disclosure, a multi-model knowledge distillation method is provided, including: [0005] Extract the features of the training image to obtain the training data; [0006] Input the training ...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V40/10G06F18/211G06F18/214G06F18/24
Inventor 张学森伊帅闫俊杰王晓刚
Owner BEIJING SENSETIME TECH DEV 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