Long-tail distribution image classification method with noise label

A classification method and labeling technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as ignoring data distribution, and achieve the effect of increasing tolerance, improving performance, and reducing impact

Active Publication Date: 2021-10-19
ZHEJIANG LAB
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing research on noisy labels usually focuses on splitting correct

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
  • Long-tail distribution image classification method with noise label
  • Long-tail distribution image classification method with noise label
  • Long-tail distribution image classification method with noise label

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0043] Noise label learning has received a lot of attention in recent years and has achieved amazing results. However, existing deep neural networks (DNNs) are still deficient in addressing noisy labels and long-tail learning. Such as Figure 1a shown, where the symmetric noise rate , when DNNs are used to fit noisy labels, fluctuations in validation accuracy explain the noise capacity of the model. Such as Figure 1b Shown, where the imbalance factor , the application of DNN in long-tail distribution learning also reflects similar characteristics, that is, DNN first fits the main category, and then gradually fits the tail category. From the above analysi...

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 a long-tail distribution image classification method with a noise label, which is used for solving the problem of image classification with both long-tail features and noise labels by learning through relaxation interval loss depended on by a sample and assisted by an anti-noise data enhancement strategy. According to data noise features, sample-dependent slack variables are introduced to relax interval constraints when sample function intervals are calculated, and then sample-dependent smooth slack losses are calculated according to sample interval classification; and according to the data long tail features, a data enhancement strategy adjusted in stages is implemented, strong enhancement and weak enhancement are performed on samples respectively, and a sample screening mechanism based on relaxation loss is provided in a formal training stage for screening noise data. The method is simple and convenient to implement and flexible in means, and remarkable classification effect improvement is achieved on long-tail data, noise data and training data with the characteristics of the long-tail data and the noise data at the same time.

Description

technical field [0001] The invention relates to the field of image classification, in particular to a method for image classification under noise labels and long-tail distribution data. Background technique [0002] In recent years, convolutional neural networks (CNNs) have been widely used in the field of computer vision. When the number of training data is fixed, the increase in the number of parameters leads to an increasingly prominent phenomenon of overfitting. In order to improve the overall performance, the demand for accurately labeled data is also increasing. However, obtaining a large number of accurately labeled samples is usually expensive. For this, non-expert crowdsourcing or systematic labeling is a practical solution, however, it is prone to mislabeling of labels. Many benchmark datasets, such as ImageNet, CIFAR-10 / -100, MNIST, QuickDraw, etc., contain 3%~10% noisy label samples. Existing studies on noisy labels usually focus on splitting correctly and mis...

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/241G06F18/214
Inventor 程乐超茅一宁冯尊磊宋明黎
Owner ZHEJIANG LAB
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