Classification and localization consistency regularized student-teacher network for semi-supervised cervical cell detection

Menglu Zhang, Xuechen Li, Linlin Shen

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Cytopathology image analysis gives an important indication of the cervical carcinoma. Automation-assisted diagnosis has received more and more attention because of its high efficiency. Thanks to the development of artificial intelligence, supervised deep learning methods have shown promising results for cervical cell detection task. However, large amounts of labeled data are quite expensive and time-consuming for acquisition. In this paper, we propose a Classification and Localization Consistency Regularized Student-Teacher Network (CLCR-STNet) with online pseudo label mining to leverage both labeled and unlabeled data for semi-supervised cervical cell detection. Both classification and localization consistency regularization are introduced to ensure that the bounding boxes predicted by the student and teacher networks are consistent. Instead of sharing the network parameters with student model, our teacher model is updated using exponential moving average (EMA). Moreover, the teacher network is used to generate high-confidence pseudo labels for unlabeled data to provide student network with more supervised information. The experiment results show that the proposed method outperforms the supervised methods learned using labeled data only.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 34th International Symposium on Computer-Based Medical Systems, CBMS 2021
EditorsJoao Rafael Almeida, Alejandro Rodriguez Gonzalez, Linlin Shen, Bridget Kane, Agma Traina, Paolo Soda, Jose Luis Oliveira
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages289-294
Number of pages6
ISBN (Electronic)9781665441216
DOIs
Publication statusPublished - Jun 2021
Externally publishedYes
Event34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021 - Virtual, Online
Duration: 7 Jun 20219 Jun 2021

Publication series

NameProceedings - IEEE Symposium on Computer-Based Medical Systems
Volume2021-June
ISSN (Print)1063-7125

Conference

Conference34th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2021
CityVirtual, Online
Period7/06/219/06/21

Keywords

  • Consistency Regularize
  • Pseudo Label
  • Semi-supervised
  • Student-Teacher network

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Classification and localization consistency regularized student-teacher network for semi-supervised cervical cell detection'. Together they form a unique fingerprint.

Cite this