Weakly Supervised Deep Metric Learning for Template Matching

Davit Buniatyan, Sergiy Popovych, Dodam Ih, Thomas Macrina, Jonathan Zung, Hyunjune Sebastian Seung

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

5 Scopus citations


Template matching by normalized cross correlation (NCC) is widely used for finding image correspondences. NCCNet improves the robustness of this algorithm by transforming image features with siamese convolutional nets trained to maximize the contrast between NCC values of true and false matches. The main technical contribution is a weakly supervised learning algorithm for the training. Unlike fully supervised approaches to metric learning, the method can improve upon vanilla NCC without receiving locations of true matches during training. The improvement is quantified through patches of brain images from serial section electron microscopy. Relative to a parameter-tuned bandpass filter, siamese convolutional nets significantly reduce false matches. The improved accuracy of the method could be essential for connectomics, because emerging petascale datasets may require billions of template matches during assembly. Our method is also expected to generalize to other computer vision applications that use template matching to find image correspondences.

Original languageEnglish (US)
Title of host publicationAdvances in Computer Vision - Proceedings of the 2019 Computer Vision Conference CVC
EditorsSupriya Kapoor, Kohei Arai
PublisherSpringer Verlag
Number of pages20
ISBN (Print)9783030177942
StatePublished - 2020
EventComputer Vision Conference, CVC 2019 - Las Vegas, United States
Duration: Apr 25 2019Apr 26 2019

Publication series

NameAdvances in Intelligent Systems and Computing
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365


ConferenceComputer Vision Conference, CVC 2019
Country/TerritoryUnited States
CityLas Vegas

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)


  • Metric learning
  • Normalized cross correlation
  • Siamese convolutional neural networks
  • Weak supervision


Dive into the research topics of 'Weakly Supervised Deep Metric Learning for Template Matching'. Together they form a unique fingerprint.

Cite this