Learning Semantic Correspondence

Minsu Cho
Nov. 30 17:25~17:55


I will present our recent approach to the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with hand-crafted features, or learning a correspondence model for appearance only. We propose instead a convolutional neural network architecture, called SCNet, for learning a geometrically plausible model for semantic correspondence. SCNet uses region proposals as matching primitives, and explicitly incorporates geometric consistency in its loss function. It is trained on image pairs obtained from the PASCAL VOC 2007 keypoint dataset, and a comparative evaluation on several standard benchmarks demonstrates that the proposed approach substantially outperforms both recent deep learning architectures and previous methods based on hand-crafted features.



Minsu Cho is an assistant professor in the department of Computer Science and Engineering at POSTECH. He obtained his PhD in 2012 from Seoul National University, Korea, and worked as a researcher (starting research position) in the Inria WILLOW team at the Department of Computer Science, École Normale Supérieure (ENS), Paris, France, until 2016. His research has focused on the interplay between computer vision and machine learning, especially in the problems of graph-based object matching and learning. His recent research investigates unsupervised or minimally-supervised object discovery, localization, matching, and tracking in images and videos.



  • 2005.03–2012.02, Ph.D (Unified master’s and doctor’s course), Seoul National University
  • 1997.03–2001.08, B.S., Department of Electrical Engineering, Seoul National University


Professional Career

  • POSTECH, Korea
    – Assistant Professor, Sep 2016–Present
  • Inria – WILLOW team / Ecole Normale Superieure, France
    – Inria Starting Researcher, Jun 2015–Aug 2016
    – Postdoctoral Research Fellow, Jun 2012–May 2015
  • Automation and Systems Research Institute, Seoul National University, Korea
    – Senior Researcher, Mar 2012–Apr 2012


Awards and Honors

  • 2011, Competition winner in rotational symmetry, Symmetry Detection Workshop, CVPR
  • 2011, Best research award, SNU BrainKorea21
  • 2010, Best presentation prize, International Computer Vision Summer School (ICVSS)
  • 2012, Samsung Humantech Thesis Prize: Gold Prize and Bronze Prize in Signal Processing
  • 2011, Samsung Humantech Thesis Prize: Silver Prize in Computer Science & Computer Engineering
  • 2010, Samsung Humantech Thesis Prize: Silver Prize in Computer Science & Computer Engineering
  • 2009, Samsung Humantech Thesis Prize: Bronze Prize in Signal Processing
  • 2008, Samsung Humantech Thesis Prize: Gold Prize in Signal Processing