Maksim Lapin (PhD Student)

MSc Maksim Lapin

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus
Location
-
Phone
Fax

Personal Information

Research Interests

  • Computer Vision (image classification)
  • Machine Learning (kernel methods)

Research Projects

Teaching

  • Teaching Assistant, Machine Learning, Winter Semester 2014 (taught by Mario Fritz and Bjoern Andres)
  • Teaching Assistant, Probabilistic Graphical Models and their Applications, Winter Semester 2013/2014 (taught by Bernt Schiele and Bjoern Andres)
  • Teaching Assistant, Machine Learning, Winter Semester 2010/2011 (taught by Matthias Hein)

Education

  • 2012–present, Ph.D. candidate in Computer Science, Max Planck Institute for Informatics
  • 2012, M.Sc. in Computer Science, Saarland University
  • 2006, Diploma in Mathematics, Belarusian State University

Personal Pages

Publications

2018

  1. Article
    D2
    “Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 7, 2018.

2017

  1. Thesis
    D2IMPR-CS
    “Image Classification with Limited Training Data and Class Ambiguity,” Universität des Saarlandes, Saarbrücken, 2017.

2016

  1. Conference paper
    D2
    “Loss Functions for Top-k Error: Analysis and Insights,” in 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, USA, 2016.

2015

  1. Conference paper
    D2
    “Efficient Output Kernel Learning for Multiple Tasks,” in Advances in Neural Information Processing Systems 28 (NIPS 2015), Montréal, Canada, 2016.
  2. Conference paper
    D2
    “Top-k Multiclass SVM,” in Advances in Neural Information Processing Systems 28 (NIPS 2015), Montréal, Canada, 2016.

2014

  1. Conference paper
    D2
    “Scalable Multitask Representation Learning for Scene Classification,” in 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, OH, USA, 2014.
  2. Article
    D2
    “Learning Using Privileged Information: SVM+ and Weighted SVM,” Neural Networks, vol. 53, 2014.
  3. Conference poster
    D2
    “Scalable Multitask Representation Learning for Scene Classification,” Scene Understanding Workshop (SUNw 2014). 2014.