research-article

Fast Mixing of Hard Negative Samples for Contrastive Learning and Use for COVID-19

Authors:

ShuiSheng ZhouAuthors Info & Claims

ICBDT '21: Proceedings of the 4th International Conference on Big Data Technologies

Pages 6 - 12

https://doi.org/10.1145/3490322.3490324

Published: 27 December 2021 Publication History

Abstract

The new type of coronavirus pneumonia (COVID-19) is spreading around the world, and one of the main reasons is the low detection efficiency and lack of detection materials. Image recognition algorithms based on deep learning are an effective method to assist epidemic detection. However, COVID-19 medical image data has the problems of difficulty in obtaining case samples and high data labeling costs. Contrastive learning algorithm is the best performing method among self-supervised learning algorithms without label training. To solve the problem of insufficient annotation data for COVID-19 medical images, this paper proposes a contrastive learning algorithm that incorporates feature synthesis components of hard negative samples. The feature of hard negative samples is a key factor to promote network training among a large number of negative samples features. Generating more hard negative samples features and adding them to the contrastive loss function for calculation allows the comparison learning algorithm to learn better semantic features. At the same time, the contrastive learning algorithm proposed in this paper is used in the transfer learning of COVID-19 CT images, which can deal with the problem of large differences between the original domain and the target domain. The algorithm proposed in this paper uses common methods of self-supervised learning to evaluate the classification accuracy of 0.798 on the COVID-CT data set, which has a significant improvement. The training method of transfer learning has better classification performance than common methods, and the classification accuracy is 0.852.

References

[1]

2020. Novel coronavirus diagnosis and treatment scheme (trial eighth edition). Chinese Journal of Clinical Infectious Diseases5 (2020), 321–328.

[2]

A Ami and B Ae. 2020. Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Systems with Applications 164 (2020).

[3]

S. Azizi, B. Mustafa, F. Ryan, Z. Beaver, J. Freyberg, J. Deaton, A. Loh, A. Karthikesalingam, S. Kornblith, and T. Chen. 2021. Big Self-Supervised Models Advance Medical Image Classification. (2021).

[4]

A. Bochkovskiy, C. Y. Wang, and Hym Liao. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection. (2020).

[5]

T. Chen, S. Kornblith, M. Norouzi, and G. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. (2020).

[6]

K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]

K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]

Huang Hong, Peng Chao, Wu Ruoyu, Tao Junli, and Zhang Jiuquan. 2020. Self-Supervised Transfer Learning of Pulmonary Nodule Classification Based on Partially Annotated CT Images. Acta Optica Sinica 40, 18 (2020), 1810003.

[9]

Y. Kalantidis, M. B. Sariyildiz, N. Pion, P. Weinzaepfel, and D. Larlus. 2020. Hard Negative Mixing for Contrastive Learning. (2020).

[10]

D. S. Kermany, M. Goldbaum, W. CaI, Ccs Valentim, H. Liang, S. L. Baxter, A. Mckeown, Y. Ge, and X. Wu. 2018. Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell 172, 5 (2018), 1122–1131.e9.

[11]

B. Li, F. Wu, S. N. Lim, S. Belongie, and K. Q. Weinberger. 2020. On Feature Normalization and Data Augmentation. (2020).

[12]

X. Li, M. Jia, M. T. Islam, L. Yu, and L. Xing. 2020. Self-supervised Feature Learning via Exploiting Multi-modal Data for Retinal Disease Diagnosis. IEEE Transactions on Medical Imaging PP, 99 (2020), 1–1.

[13]

Z. Li, W. Zhao, F. Shi, L. Qi, X Xie, Y. Wei, Z. Ding, Y. Gao, S. Wu, and J. Liu. 2021. A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning. Medical Image Analysis(2021).

[14]

Y. Oh, S. Park, and J. C. Ye. 2020. Deep Learning COVID-19 Features on CXR using Limited Training Data Sets. arXiv (2020).

[15]

M. Raghu, C. Zhang, J Kleinberg, and S. Bengio. 2019. Transfusion: Understanding Transfer Learning for Medical Imaging. (2019).

[16]

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, and M. Bernstein. 2014. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision(2014), 1–42.

[17]

Y. H. Wu, S. H. Gao, J. Mei, J. Xu, and M. M. Cheng. 2021. JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation. IEEE Transactions on Image Processing PP, 99 (2021), 1–1.

[18]

Wang S Y, Li N, Zhang X Y, and Wang Q. 2020. Recent advances on detection methods of novel coronavirus SARS-CoV-2. Research and Exploration in Laboratory5 (2020), 1–7.

[19]

Xingyi Yang, Xuehai He, J. Zhao, Y. Zhang, S. Zhang, and P. Xie. 2020. COVID-CT-Dataset: A CT Scan Dataset about COVID-19. (2020).

[20]

M. Ye, X. Zhang, P. C. Yuen, and S. F. Chang. 2020. Unsupervised Embedding Learning via Invariant and Spreading Instance Feature. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]

S. Yun, D. Han, S. Chun, S. J. Oh, Y. Yoo, and J. Choe. [n.d.]. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features. In International Conference on Computer Vision.

[22]

H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz. 2017. mixup: Beyond Empirical Risk Minimization. (2017).

Cited By

VanBerlo BHoey JWong A(2024)A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasoundBMC Medical Imaging10.1186/s12880-024-01253-024:1Online publication date: 6-Apr-2024
https://doi.org/10.1186/s12880-024-01253-0
Huang SPareek AJensen MLungren MYeung SChaudhari A(2023)Self-supervised learning for medical image classification: a systematic review and implementation guidelinesnpj Digital Medicine10.1038/s41746-023-00811-06:1Online publication date: 26-Apr-2023
https://doi.org/10.1038/s41746-023-00811-0
Wang WAhn EFeng DKim J(2023)A Review of Predictive and Contrastive Self-supervised Learning for Medical ImagesMachine Intelligence Research10.1007/s11633-022-1406-420:4(483-513)Online publication date: 3-Jun-2023
https://doi.org/10.1007/s11633-022-1406-4

Index Terms

Fast Mixing of Hard Negative Samples for Contrastive Learning and Use for COVID-19
1. Applied computing
  1. Life and medical sciences
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning

Index terms have been assigned to the content through auto-classification.

Recommendations

Mixing up contrastive learning: Self-supervised representation learning for time series
Highlights
- A contrastive learning framework for time series motivated through label smoothing.
Abstract
The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. ...
Negative samples selecting strategy for graph contrastive learning
Abstract
Graph neural networks (GNNs) have emerged as a successful method on graph structured data. Limited by expensive labeled data, contrastive learning has been adopted to the graph domain. In most existing node-level graph contrastive ...
Unsupervised Few-Shot Learning via Positive Expansions and Negative Proxies
Advanced Intelligent Computing Technology and Applications
Abstract
Few-shot learning has made significant progress recently thanks to pre-training methods and meta-learning approaches. These methods, however, require an extensive labeled dataset that is difficult to obtain. We propose an unsupervised few-shot ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICBDT '21: Proceedings of the 4th International Conference on Big Data Technologies

September 2021

189 pages

ISBN:9781450385091

DOI:10.1145/3490322

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 December 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICBDT 2021

ICBDT 2021: 2021 4th International Conference on Big Data Technologies

September 24 - 26, 2021

Zibo, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
97
Total Downloads

Downloads (Last 12 months)34
Downloads (Last 6 weeks)1

Reflects downloads up to 02 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

VanBerlo BHoey JWong A(2024)A survey of the impact of self-supervised pretraining for diagnostic tasks in medical X-ray, CT, MRI, and ultrasoundBMC Medical Imaging10.1186/s12880-024-01253-024:1Online publication date: 6-Apr-2024
https://doi.org/10.1186/s12880-024-01253-0
Huang SPareek AJensen MLungren MYeung SChaudhari A(2023)Self-supervised learning for medical image classification: a systematic review and implementation guidelinesnpj Digital Medicine10.1038/s41746-023-00811-06:1Online publication date: 26-Apr-2023
https://doi.org/10.1038/s41746-023-00811-0
Wang WAhn EFeng DKim J(2023)A Review of Predictive and Contrastive Self-supervised Learning for Medical ImagesMachine Intelligence Research10.1007/s11633-022-1406-420:4(483-513)Online publication date: 3-Jun-2023
https://doi.org/10.1007/s11633-022-1406-4

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents