Lifelong Learning

Team

Daphne AuerNiklas Penzel, Paul Bodesheim

Motivation

Lifelong learning denotes a concept for continuous learning from data streams that typically become available during the application of a recognition system, e.g., additional images captured during a visual monitoring study. Instead of only applying a fixed model pre-trained on an initial dataset, lifelong learning aims at leveraging the additional data collected during an application in order to improve the recognition model over time. It incorporates active learning to exploit human feedback via annotations of unlabeled samples that have an impact on model training. Furthermore, incremental learning is required to update model parameters effectively and efficiently. In unconstrained environments and open-world scenarios, novelty detection also needs to be considered.

Publications

2019
Björn Barz, Christoph Käding, Joachim Denzler:
Information-Theoretic Active Learning for Content-Based Image Retrieval.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 650-666. 2019.
[bibtex] [pdf] [doi] [code] [supplementary] [abstract]
2017
Erik Rodner, Alexander Freytag, Paul Bodesheim, Björn Fröhlich, Joachim Denzler:
Large-Scale Gaussian Process Inference with Generalized Histogram Intersection Kernels for Visual Recognition Tasks.
International Journal of Computer Vision (IJCV). 121 (2) : pp. 253-280. 2017.
[bibtex] [pdf] [web] [doi] [abstract]
Jonas Jäger, Claudia Kruschel, Stewart T. Schultz, Dubravko Pedjo, Viviane Wolff, Klaus Fricke-Neuderth, Joachim Denzler:
Underwater and in the Cloud: Web-based Machine Learning for Fish Video Analysis.
52nd European Marine Biology Symposium. 2017.
[bibtex] [pdf]
2016
Alexander Freytag:
Lifelong Learning for Visual Recognition Systems.
2016. ISBN 9783843929950
[bibtex] [pdf] [web]
Christoph Käding, Alexander Freytag, Erik Rodner, Andrea Perino, Joachim Denzler:
Large-scale Active Learning with Approximated Expected Model Output Changes.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 179-191. 2016.
[bibtex] [pdf] [web] [doi] [code] [supplementary] [abstract]
Christoph Käding, Erik Rodner, Alexander Freytag, Joachim Denzler:
Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes.
NIPS Workshop on Continual Learning and Deep Networks (NIPS-WS). 2016.
[bibtex] [pdf] [web] [abstract]
Christoph Käding, Erik Rodner, Alexander Freytag, Joachim Denzler:
Fine-tuning Deep Neural Networks in Continuous Learning Scenarios.
ACCV Workshop on Interpretation and Visualization of Deep Neural Nets (ACCV-WS). 2016.
[bibtex] [pdf] [web] [supplementary] [abstract]
Christoph Käding, Erik Rodner, Alexander Freytag, Joachim Denzler:
Watch, Ask, Learn, and Improve: A Lifelong Learning Cycle for Visual Recognition.
European Symposium on Artificial Neural Networks (ESANN). Pages 381-386. 2016.
[bibtex] [pdf] [code] [presentation] [abstract]
2015
Christoph Käding, Alexander Freytag, Erik Rodner, Paul Bodesheim, Joachim Denzler:
Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Pages 4343-4352. 2015.
[bibtex] [pdf] [web] [doi] [code] [presentation] [supplementary] [abstract]
Paul Bodesheim, Alexander Freytag, Erik Rodner, Joachim Denzler:
Local Novelty Detection in Multi-class Recognition Problems.
IEEE Winter Conference on Applications of Computer Vision (WACV). Pages 813-820. 2015.
[bibtex] [pdf] [web] [doi] [supplementary] [abstract]
2014
Alexander Freytag, Erik Rodner, Joachim Denzler:
Birds of a Feather Flock Together - Local Learning of Mid-level Representations for Fine-grained Recognition.
ECCV Workshop on Parts and Attributes (ECCV-WS). 2014.
[bibtex] [pdf] [web] [code] [presentation]
Alexander Freytag, Erik Rodner, Joachim Denzler:
Selecting Influential Examples: Active Learning with Expected Model Output Changes.
European Conference on Computer Vision (ECCV). Pages 562-577. 2014.
[bibtex] [pdf] [presentation] [supplementary] [abstract]
Alexander Freytag, Erik Rodner, Trevor Darrell, Joachim Denzler:
Exemplar-specific Patch Features for Fine-grained Recognition.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 144-156. 2014.
[bibtex] [pdf] [code] [supplementary] [abstract]
Björn Barz, Erik Rodner, Joachim Denzler:
ARTOS -- Adaptive Real-Time Object Detection System.
arXiv preprint arXiv:1407.2721. 2014.
[bibtex] [pdf] [web] [code] [abstract]
Daniel Göhring, Judy Hoffman, Erik Rodner, Kate Saenko, Trevor Darrell:
Interactive Adaptation of Real-Time Object Detectors.
International Conference on Robotics and Automation (ICRA). Pages 1282-1289. 2014.
[bibtex] [pdf] [web] [abstract]
Judy Hoffman, Erik Rodner, Jeff Donahue, Brian Kulis, Kate Saenko:
Asymmetric and Category Invariant Feature Transformations for Domain Adaptation.
International Journal of Computer Vision (IJCV). 109 (1-2) : pp. 28-41. 2014.
[bibtex] [pdf] [web] [doi] [abstract]
Sergio Guadarrama, Erik Rodner, Kate Saenko, Ning Zhang, Ryan Farrell, Jeff Donahue, Trevor Darrell:
Open-vocabulary Object Retrieval.
Robotics Science and Systems (RSS). Pages 41, ISBN 978-0-9923747-0-9. 2014. Awarded with an AAAI invited talk
[bibtex] [pdf] [web] [abstract]
2013
Alexander Freytag, Erik Rodner, Paul Bodesheim, Joachim Denzler:
Labeling examples that matter: Relevance-Based Active Learning with Gaussian Processes.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 282-291. 2013.
[bibtex] [pdf] [web] [doi] [code] [supplementary] [abstract]
Alexander Lütz, Erik Rodner, Joachim Denzler:
I Want To Know More: Efficient Multi-Class Incremental Learning Using Gaussian Processes.
Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications (PRIA). 23 (3) : pp. 402-407. 2013.
[bibtex] [pdf]
Erik Rodner, Judy Hoffman, Jeff Donahue, Trevor Darrell, Kate Saenko:
Scalable Transform-based Domain Adaptation.
ICCV Workshop on Visual Domain Adaptation (ICCV-WS). 2013.
[bibtex] [pdf]
Erik Rodner, Judy Hoffman, Jeff Donahue, Trevor Darrell, Kate Saenko:
Towards Adapting ImageNet to Reality: Scalable Domain Adaptation with Implicit Low-rank Transformations.
arXiv preprint arXiv:1308.4200. 2013.
[bibtex] [pdf]
Erik Rodner, Judy Hoffman, Jeff Donahue, Trevor Darrell, Kate Saenko:
Transform-based Domain Adaptation for Big Data.
NIPS Workshop on New Directions in Transfer and Multi-Task Learning (NIPS-WS). 2013. abstract version of arXiv:1308.4200
[bibtex] [pdf] [abstract]
Jeff Donahue, Judy Hoffman, Erik Rodner, Kate Saenko, Trevor Darrell:
Semi-Supervised Domain Adaptation with Instance Constraints.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Pages 668-675. 2013.
[bibtex] [pdf]
Joachim Denzler, Erik Rodner, Paul Bodesheim, Alexander Freytag:
Beyond the closed-world assumption: The importance of novelty detection and open set recognition.
GCPR/DAGM Workshop on Unsolved Problems in Pattern Recognition and Computer Vision (GCPR-WS): Extended Abstract + Oral Presentation. 2013.
[bibtex] [pdf] [web]
Judy Hoffman, Erik Rodner, Jeff Donahue, Trevor Darrell, Kate Saenko:
Efficient Learning of Domain-invariant Image Representations.
International Conference on Learning Representations (ICLR). 2013.
[bibtex] [pdf]
Michael Kemmler, Erik Rodner, Esther-Sabrina Wacker, Joachim Denzler:
One-class Classification with Gaussian Processes.
Pattern Recognition. 46 (12) : pp. 3507-3518. 2013.
[bibtex] [pdf] [doi]
Paul Bodesheim, Alexander Freytag, Erik Rodner, Joachim Denzler:
An Efficient Approximation for Gaussian Process Regression.
2013. Technical Report TR-FSU-INF-CV-2013-01
[bibtex] [pdf]
Paul Bodesheim, Alexander Freytag, Erik Rodner, Joachim Denzler:
Approximations of Gaussian Process Uncertainties for Visual Recognition Problems.
Scandinavian Conference on Image Analysis (SCIA). Pages 182-194. 2013.
[bibtex] [pdf] [web] [doi] [abstract]
Paul Bodesheim, Alexander Freytag, Erik Rodner, Michael Kemmler, Joachim Denzler:
Kernel Null Space Methods for Novelty Detection.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Pages 3374-3381. 2013.
[bibtex] [pdf] [web] [doi] [code] [presentation] [abstract]
2012
Erik Rodner:
Lernen mit wenigen Beispielen für die visuelle Objekterkennung.
Ausgezeichnete Informatikdissertationen 2011. 2012. in german
[bibtex] [pdf] [web]
Paul Bodesheim, Erik Rodner, Alexander Freytag, Joachim Denzler:
Divergence-Based One-Class Classification Using Gaussian Processes.
British Machine Vision Conference (BMVC). Pages 50.1-50.11. 2012.
[bibtex] [pdf] [web] [doi] [presentation] [abstract]
2011
Alexander Lütz, Erik Rodner, Joachim Denzler:
Efficient Multi-Class Incremental Learning Using Gaussian Processes.
Open German-Russian Workshop on Pattern Recognition and Image Understanding (OGRW). Pages 182-185. 2011.
[bibtex] [pdf] [abstract]
Erik Rodner:
Learning from Few Examples for Visual Recognition Problems.
2011.
[bibtex] [pdf] [web]
Erik Rodner, Joachim Denzler:
Learning with Few Examples for Binary and Multiclass Classification Using Regularization of Randomized Trees.
Pattern Recognition Letters. 32 (2) : pp. 244-251. 2011.
[bibtex] [pdf]
2010
Erik Rodner, Joachim Denzler:
One-Shot Learning of Object Categories using Dependent Gaussian Processes.
Symposium of the German Association for Pattern Recognition (DAGM). Pages 232-241. 2010.
[bibtex] [pdf]
Michael Kemmler, Erik Rodner, Joachim Denzler:
One-Class Classification with Gaussian Processes.
Asian Conference on Computer Vision (ACCV). Pages 489-500. 2010.
[bibtex] [pdf] [presentation]
2009
Erik Rodner, Joachim Denzler:
Learning with Few Examples by Transferring Feature Relevance.
Symposium of the German Association for Pattern Recognition (DAGM). Pages 252-261. 2009.
[bibtex] [pdf]
2008
Erik Rodner, Joachim Denzler:
Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees.
Vision, Modelling, and Visualization Workshop (VMV). Pages 159-168. 2008.
[bibtex] [pdf]