Maksim Lapin (PhD Student)

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

2017
Image Classification with Limited Training Data and Class Ambiguity
M. Lapin
PhD Thesis, Universität des Saarlandes, 2017
Abstract
Modern image classification methods are based on supervised learning algorithms that require labeled training data. However, only a limited amount of annotated data may be available in certain applications due to scarcity of the data itself or high costs associated with human annotation. Introduction of additional information and structural constraints can help improve the performance of a learning algorithm. In this thesis, we study the framework of learning using privileged information and demonstrate its relation to learning with instance weights. We also consider multitask feature learning and develop an efficient dual optimization scheme that is particularly well suited to problems with high dimensional image descriptors. Scaling annotation to a large number of image categories leads to the problem of class ambiguity where clear distinction between the classes is no longer possible. Many real world images are naturally multilabel yet the existing annotation might only contain a single label. In this thesis, we propose and analyze a number of loss functions that allow for a certain tolerance in top k predictions of a learner. Our results indicate consistent improvements over the standard loss functions that put more penalty on the first incorrect prediction compared to the proposed losses. All proposed learning methods are complemented with efficient optimization schemes that are based on stochastic dual coordinate ascent for convex problems and on gradient descent for nonconvex formulations.
2016
Loss Functions for Top-k Error: Analysis and Insights
M. Lapin, M. Hein and B. Schiele
29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification
M. Lapin, M. Hein and B. Schiele
Technical Report, 2016
(arXiv: 1612.03663)
Abstract
Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and the smooth multiclass SVM are surprisingly competitive in top-k error uniformly across all k, which can be explained by our analysis of multiclass top-k calibration. Further improvements for a specific k are possible with a number of proposed top-k loss functions. Second, we use the top-k methods to explore the transition from multiclass to multilabel learning. In particular, we find that it is possible to obtain effective multilabel classifiers on Pascal VOC using a single label per image for training, while the gap between multiclass and multilabel methods on MS COCO is more significant. Finally, our contribution of efficient algorithms for training with the considered top-k and multilabel loss functions is of independent interest.
2015
Efficient Output Kernel Learning for Multiple Tasks
P. Jawanpuria, M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
Top-k Multiclass SVM
M. Lapin, M. Hein and B. Schiele
Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015
2014
Scalable Multitask Representation Learning for Scene Classification
M. Lapin, B. Schiele and M. Hein
2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), 2014
Learning Using Privileged Information: SVM+ and Weighted SVM
M. Lapin, M. Hein and B. Schiele
Neural Networks, Volume 53, 2014
Scalable Multitask Representation Learning for Scene Classification
M. Lapin, B. Schiele and M. Hein
Scene Understanding Workshop (SUNw 2014), 2014