Insights from classifying visual concepts with multiple kernel learning

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

  • Alexander Binder
  • Shinichi Nakajima
  • Marius Kloft
  • Christina Müller
  • Wojciech Samek
  • Ulf Brefeld
  • Klaus Robert Müller
  • Motoaki Kawanabe

Combining information from various image features has become a standard technique in concept recognition tasks. However, the optimal way of fusing the resulting kernel functions is usually unknown in practical applications. Multiple kernel learning (MKL) techniques allow to determine an optimal linear combination of such similarity matrices. Classical approaches to MKL promote sparse mixtures. Unfortunately, 1-norm regularized MKL variants are often observed to be outperformed by an unweighted sum kernel. The main contributions of this paper are the following: we apply a recently developed non-sparse MKL variant to state-of-the-art concept recognition tasks from the application domain of computer vision. We provide insights on benefits and limits of non-sparse MKL and compare it against its direct competitors, the sum-kernel SVM and sparse MKL. We report empirical results for the PASCAL VOC 2009 Classification and ImageCLEF2010 Photo Annotation challenge data sets. Data sets (kernel matrices) as well as further information are available at http://doc.ml.tuberlin.de/image_mkl/(Accessed 2012 Jun 25).

Original languageEnglish
Article numbere38897
JournalPLoS ONE
Volume7
Issue number8
ISSN1932-6203
DOIs
Publication statusPublished - 24.08.2012
Externally publishedYes

    Research areas

  • Informatics - concept formation, controlled study, histogram, image display, intermethod comparison, kernel method, machine learning, scoring system, support vector machine, task performance, validity
  • Business informatics

Documents

DOI

Recently viewed

Publications

  1. A Wavelet Based Algorithm without a Priori Knowledge of Noise Level for Gross Errors Detection
  2. Inner loop model predictive control and outer loop PI reference governor for PMSMs with input and state saturation for torque control
  3. Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling
  4. Using Technologies for Foreign Language Learning in Inclusive Settings
  5. Fostering Circularity: Building a Local Community and Implementing Circular Processes
  6. Advanced Neural Classifier-Based Effective Human Assistance Robots Using Comparable Interactive Input Assessment Technique
  7. Supervised clustering of streaming data for email batch detection
  8. Neural Combinatorial Optimization on Heterogeneous Graphs
  9. Implicit statistical learning and working memory predict EFL development and written task outcomes in adolescents
  10. Unidimensional and Multidimensional Methods for Recurrence Quantification Analysis with crqa
  11. Different approaches to learning from errors: Comparing the effectiveness of high reliability and error management approaches
  12. Dynamic adjustment of dispatching rule parameters in flow shops with sequence-dependent set-up times
  13. Evaluating the construct validity of Objective Personality Tests using a multitrait-multimethod-Multioccasion-(MTMM-MO)-approach
  14. A Wavelet Packet Tree Denoising Algorithm for Images of Atomic-Force Microscopy
  15. A coding scheme to analyse global text processing in computer supported collaborative learning: What eye movements can tell us
  16. Integrating Mobile Devices into AAL-Environments using Knowledge based Assistance Systems
  17. Ant colony optimization algorithm and artificial immune system applied to a robot route
  18. Development of a Didactic Graphical Simulation Interface on MATLAB for Systems Control
  19. Knowledge Graph Question Answering Using Graph-Pattern Isomorphism
  20. Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?
  21. Random measurement and prediction errors limit the practical relevance of two velocity sensors to estimate the 1RM back squat
  22. Towards a Dynamic Interpretation of Subjective and Objective Values
  23. Substructure, subgraph, and walk counts as measures of the complexity of graphs and molecules.
  24. Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
  25. Building Assistance Systems using Distributed Knowledge Representations
  26. DialogueMaps: Supporting interactive transdisciplinary dialogues with a web-based tool for multi-layer knowledge maps
  27. The learning net - an interactive representation of shared knowledge
  28. Set-oriented numerical computation of rotation sets
  29. Isocodal and isospectral points, edges, and pairs in graphs and how to cope with them in computerized symmetry recognition
  30. Making an Impression Through Openness
  31. A model predictive control for an aggregate actuator with a self-tuning initial condition procedure in combustion engines
  32. A discrete approximate solution for the asymptotic tracking problem in affine nonlinear systems
  33. Multi-Parallel Sending Coils for Movable Receivers in Inductive Charging Systems
  34. Control of a Sun Tracking Robot Based on Adaptive Sliding Mode Control with Kalman Filtering and Model Predictive Control
  35. Anomaly detection in formed sheet metals using convolutional autoencoders
  36. Framework for setting up and operating biobanks