Readspeaker menu

Dipl.-Inf. Alexander Freytag

Former Research Associate

Dipl.-Inf. Alexander Freytag

Contact

address: 
Lehrstuhl Digitale Bildverarbeitung
Institut für Informatik
Friedrich-Schiller-Universität Jena
Ernst-Abbe-Platz 2
D-07743 Jena




phone: 
+49 3641 9 46428
room:  1221
e-mail:

Research topics

Lifelong learning for Visual Recognition Systems:

Further interests:

  • Visual recognition tasks, including object detection and localization
  • Pattern recognition and machine learning in computer vision
  • Interactive image retrieval
  • Deep learning in computer vision

Curriculum Vitae

  • focus on computer vision
  • minor subject physics
  • 2010: student research project "Enhencements for the license plate recognition system LprJ - confidence measures for plate hypotheses"
  • 2011: diploma thesis "Image based kernel functions - robust classification and semi-supervised object localization by optimization of hyperparameters" pdf (16.5MB)

Publications (main research topics)

  • Large-Scale Gaussian Processes using Histogram Intersection Kernels

  overviewGPHIK.png



hikSemSeg.png

[Rodner16_LGP]

Erik Rodner and Alexander Freytag and Paul Bodesheim and Björn Fröhlich and Joachim Denzler. Large-Scale Gaussian Process Inference with Generalized Histogram Intersection Kernels for Visual Recognition Tasks. International Journal of Computer Vision (IJCV). 2016. (accepted for publication). [pdf] [bib]

[Rodner12:LGP]

Erik Rodner and Alexander Freytag and Paul Bodesheim and Joachim Denzler. Large-Scale Gaussian Process Classification with Flexible Adaptive Histogram Kernels. European Conference on Computer Vision (ECCV). 2012. 85--98. [pdf] [bib] [project page]

[Freytag12:RUC]

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels. Asian Conference on Computer Vision (ACCV). 2012. 511--524. (Oral). [pdf] [bib] [project page] Best Paper Honorable Mention

[Freytag12:BCL]

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Beyond Classification - Large-scale Gaussian Process Inference and Uncertainty Prediction. Big Data Meets Computer Vision: First International Workshop on Large Scale Visual Recognition and Retrieval (NIPS Workshop). 2012. [pdf] [bib]

[Freytag12:ESS]

Alexander Freytag and Björn Fröhlich and Erik Rodner and Joachim Denzler. Efficient Semantic Segmentation with Gaussian Processes and Histogram Intersection Kernels. International Conference on Pattern Recognition (ICPR). 2012. 3313--3316. (Oral). [pdf] [bib] [project page]



  • Active Learning

  ActiveLearning

[Kaeding15_ALD]

Christoph Käding and Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. 4343-4352. [pdf] [bib] [presentation] [supplementary]

[Freytag14_SIE]

Alexander Freytag and Erik Rodner and Joachim Denzler. Selecting Influential Examples: Active Learning with Expected Model Output Changes. European Conference on Computer Vision (ECCV). 2014. 562--577. [pdf] [supplementary material] [bib]

[Freytag13:LET]

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Labeling examples that matter: Relevance-Based Active Learning with Gaussian Processes. German Conference on Pattern Recognition (GCPR). 2013. 282--291. (Oral). [pdf] [supplementary material] [bib] [code]

[Freytag12:RUC]

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels. Asian Conference on Computer Vision (ACCV). 2012. 511--524. (Oral). [pdf] [bib] [project page] Best Paper Honorable Mention

[Freytag12:BCL]

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler. Beyond Classification - Large-scale Gaussian Process Inference and Uncertainty Prediction. Big Data Meets Computer Vision: First International Workshop on Large Scale Visual Recognition and Retrieval (NIPS Workshop). 2012. [pdf] [bib]



  • One-Class Classification and Novelty Detection

  overviewKNFSTforNoveltyDetection


overviewNovBasedOCC

[Bodesheim15:LND]

Paul Bodesheim and Alexander Freytag and Erik Rodner and Joachim Denzler. Local Novelty Detection in Multi-class Recognition Problems. IEEE Winter Conference on Applications of Computer Vision (WACV). 2015. 813-820. [pdf] [bib]

[Bodesheim13:KNS]

Paul Bodesheim and Alexander Freytag and Erik Rodner and Michael Kemmler and Joachim Denzler. Kernel Null Space Methods for Novelty Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2013. 3374--3381. [pdf] [bib]

[Bodesheim12:DOC]

Paul Bodesheim and Erik Rodner and Alexander Freytag and Joachim Denzler. Divergence-Based One-Class Classification Using Gaussian Processes. British Machine Vision Conference (BMVC). 2012. 50.1--50.11 . [pdf] [bib] [project page]



  • Fine-grained Recognition

  interactive image retrieval

[Freytag15:IIR]

Alexander Freytag and Alena Schadt and Joachim Denzler. Interactive Image Retrieval for Biodiversity Research. German Conference on Pattern Recognition (GCPR). 2015. (accepted for publication). (Oral). [pdf] [bib]

  Exemplar-specific Patch Features for Fine-grained Recognition

[Freytag14:ESP]

Alexander Freytag and Erik Rodner and Trevor Darrell and Joachim Denzler. Exemplar-specific Patch Features for Fine-grained Recognition. German Conference on Pattern Recognition (GCPR). 2014.144--156. (Oral). [pdf] [bib] [code]

[Freytag14:BFF]

Alexander Freytag and Erik Rodner and Joachim Denzler. Birds of a Feather Flock Together - Local Learning of Mid-level Representations for Fine-grained Recognition. ECCV Workshop on Parts and Attributes. 2014. [pdf] [bib] [code]
  PartTransferForFineGrainedRecognition

[Goering14:NPT]

Christoph Göring and Erik Rodner and Alexander Freytag and Joachim Denzler. Nonparametric Part Transfer for Fine-grained Recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2014.[pdf] [bib] [code]
  PipelineOfFGSystem

[Goering13:FGC]

Christoph Göring and Alexander Freytag and Erik Rodner and Joachim Denzler. Fine-grained Categorization - Short Summary of our Entry for the ImageNet Challenge 2012. arXiv preprint arXiv:1310.4759. 2013. [pdf] [bib]


  • Incremental Learning        

  Incremental Learning Scenario.png

[Luetz13:IWT]

Alexander Lütz and Erik Rodner and Joachim Denzler. I Want To Know More -Efficient Multi-Class Incremental Learning Using Gaussian Processes. Pattern Recognition and Image Analysis. 2013. Vol. 23. No. 3. 402--407. [pdf] [bib]

[Luetz11:EIL]

Alexander Lütz and Erik Rodner and Joachim Denzler. Efficient Multi-Class Incremental Learning Using Gaussian Processes. Open German-Russian Workshop on Pattern Recognition and Image Understanding (OGRW). 2011.182--185. (Oral). [pdf] [bib]



Publications (side topics)

  • Visual Feature Analysis

  fromBowToImg

[Freytag14:STB]

Alexander Freytag and Johannes Rühle and Paul Bodesheim and Erik Rodner and Joachim Denzler: Seeing through bag-of-visual-word glasses: towards understanding quantization effects in feature extraction methods. ICPR Workshop on Features and Structures (FEAST). 2014. [extendedAbstact] [bib] [techReport] [poster]
Best Poster Award


  • Robust Classification and Semi-supervised Object Localization

  Robustification of Training Images

[Luetz11:RC]

Alexander Lütz. Robust Classification and Semi-Supervised Object Localization with Gaussian Processes. Annual Symposium of the German Association for Pattern Recognition (DAGM). 2011. 456--461. [pdf] [bib]


  • Technical Report: Approximating Gaussian Process Regression

  ApproxGP_RegExample

[Bodesheim13:AOG]

Paul Bodesheim and Alexander Freytag and Erik Rodner and Joachim Denzler. Approximations of Gaussian Process Uncertainties for Visual Recognition Problems.> Scandinavian Conference on Image Analysis (SCIA). 2013. 182--194. [pdf] [bib]

[Bodesheim13:AEA]

Paul Bodesheim and Alexander Freytag and Erik Rodner and Joachim Denzler. An Efficient Approximation for Gaussian Process Regression. Technical Report TR-FSU-INF-CV-2013-01, Computer Vision Group, Friedrich Schiller University Jena, Germany 2013. [pdf] [bib]



Videos


Complete List of Publications

  • Publications after marriage (A. Freytag)


  • Publications before marriage (A. Lütz)



Locations of Site Visitors
  LinkedIn Profil von Alexander Freytag  Alexander Freytag