Applying of Adaptive Threshold Non-maximum Suppression to Pneumonia Detection

Hao Teng, Huijuan Lu, Minchao Ye, Ke Yan, Zhigang Gao, Qun Jin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Hyper-parameters in deep learning are sensitive to prediction results. Non-maximum suppression (NMS) is an indispensable method for the object detection pipelines. NMS uses a pre-defined threshold algorithm to suppress the bounding boxes while their overlaps are not significant. We found that the pre-defined threshold is a hyper-parameter determined by empirical knowledge. We propose an adaptive threshold NMS that uses different thresholds to suppress the bounding boxes whose overlaps are not significant. The proposed adaptive threshold NMS algorithm provides improvements on Faster R-CNN with the AP metric on pneumonia dataset. Furthermore, we intend to propose more methods to optimize the hyper-parameters.

Original languageEnglish
Title of host publicationBio-inspired Computing
Subtitle of host publicationTheories and Applications - 14th International Conference, BIC-TA 2019, Revised Selected Papers
EditorsLinqiang Pan, Jing Liang, Boyang Qu
PublisherSpringer
Pages518-528
Number of pages11
ISBN (Print)9789811534140
DOIs
Publication statusPublished - 2020
Event14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019 - Zhengzhou, China
Duration: 2019 Nov 222019 Nov 25

Publication series

NameCommunications in Computer and Information Science
Volume1160 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019
CountryChina
CityZhengzhou
Period19/11/2219/11/25

Keywords

  • Adaptive threshold
  • Hyper-parameters
  • NMS
  • Pneumonia detection

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Applying of Adaptive Threshold Non-maximum Suppression to Pneumonia Detection'. Together they form a unique fingerprint.

  • Cite this

    Teng, H., Lu, H., Ye, M., Yan, K., Gao, Z., & Jin, Q. (2020). Applying of Adaptive Threshold Non-maximum Suppression to Pneumonia Detection. In L. Pan, J. Liang, & B. Qu (Eds.), Bio-inspired Computing: Theories and Applications - 14th International Conference, BIC-TA 2019, Revised Selected Papers (pp. 518-528). (Communications in Computer and Information Science; Vol. 1160 CCIS). Springer. https://doi.org/10.1007/978-981-15-3415-7_43