A data self-distillation method based on batch processing knowledge ensemble (BAKE)

A distillation method and knowledge integration technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as error supervision, increased calculation and memory costs, and inability to fully consider different types of samples to avoid errors Supervision and cost reduction effects

Pending Publication Date: 2021-12-31
FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a data self-distillation method based on batch processing knowledge integration (BAKE), so as to solve the problem that different types

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
  • A data self-distillation method based on batch processing knowledge ensemble (BAKE)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0023] see figure 1 , the present invention provides a technical solution: a data self-distillation method based on batch knowledge integration (BAKE), the data self-distillation method comprises the following steps:

[0024] S1: Given a small batch of samples and a network in training, store similar samples;

[0025] S2: Avoid self-awareness reinforcement and normalize the affinity matrix A;

[0026] S3: Predict the samples in a batch, and then get the soft...

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 discloses the technical field of target detection, and particularly relates to a data self-distillation method based on batch processing knowledge ensemble (BAKE), which comprises the following steps: S1, giving a small batch of samples and a network in training, and storing similar samples; s2, avoiding self-cognition enhancement, and normalizing the affinity matrix A; s3, predicting samples in one batch, and then obtaining and forming a soft learning target; s4, realizing complete integration of knowledge. Compared with an existing knowledge integration method, the problem that traditional knowledge integration needs to be processed through an additional network or branch is solved, the needed calculation amount and memory overhead are saved, BAKE is applied to a network architecture, the classification performance of the network architecture can be improved, and wrong supervision caused in the processing process is avoided.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a data self-distillation method based on batch knowledge integration (BAKE). Background technique [0002] In target detection, better target generation will lead to better detection accuracy and classification performance of the network, where the integration of knowledge has been proven to generate better soft targets, but the knowledge integration of multiple networks will bring Large amount of calculation and memory overhead, in the absence of knowledge integration, due to the limited amount of information carried by the network, good targets cannot be generated, thereby limiting the performance of the network, so it is necessary to develop a good knowledge integration data Self-distillation method. [0003] However, due to technical reasons, most technicians nowadays generally adopt the integration method of multiple networks or multiple branches. However, there ar...

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): G06K9/62G06N3/04G06N3/08G06N20/00
CPCG06N3/08G06N20/00G06N3/047G06F18/241G06F18/2415
Inventor 王华龙李泽辉吴均城杨海东
Owner FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
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