Active Learning

Team

Niklas PenzelClemens-Alexander Brust, Paul Bodesheim

Motivation

Although labeled data lies at the very core of most computer vision systems, obtaining labeled data that is useful and reliable is commonly a crucial problem. To reduce the amount of manual labeling, active learning techniques aim at explicitly picking samples that are actually worth being labeled with respect to the problem on hand. In this area of research, we are interested in modeling the “worthiness” of an unlabeled sample and to apply our algorithms to human-in-the-loop recognition systems.

Publications

2022
Paul Bodesheim, Jan Blunk, Matthias Körschens, Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research. Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes.
Mammalian Biology. 102 : pp. 875-897. 2022.
[bibtex] [web] [doi] [abstract]
2021
Clemens-Alexander Brust, Björn Barz, Joachim Denzler:
Carpe Diem: A Lifelong Learning Tool for Automated Wildlife Surveillance.
Computer Science for Biodiversity Workshop (CS4Biodiversity), INFORMATIK 2021. Pages 417-423. 2021.
[bibtex] [pdf] [doi]
Clemens-Alexander Brust, Björn Barz, Joachim Denzler:
Self-Supervised Learning from Semantically Imprecise Data.
arXiv preprint arXiv:2104.10901. 2021.
[bibtex] [pdf] [abstract]
Daphne Auer, Paul Bodesheim, Christian Fiderer, Marco Heurich, Joachim Denzler:
Minimizing the Annotation Effort for Detecting Wildlife in Camera Trap Images with Active Learning.
Computer Science for Biodiversity Workshop (CS4Biodiversity), INFORMATIK 2021. Pages 547-564. 2021.
[bibtex] [pdf] [doi] [abstract]
Niklas Penzel, Christian Reimers, Clemens-Alexander Brust, Joachim Denzler:
Investigating the Consistency of Uncertainty Sampling in Deep Active Learning.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 159-173. 2021.
[bibtex] [pdf] [web] [doi] [abstract]
2020
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
Active and Incremental Learning with Weak Supervision.
Künstliche Intelligenz (KI). 2020.
[bibtex] [pdf] [doi] [abstract]
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]
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
Active Learning for Deep Object Detection.
International Conference on Computer Vision Theory and Applications (VISAPP). Pages 181-190. 2019.
[bibtex] [pdf] [doi] [abstract]
2017
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
You Have To Look More Than Once: Active and Continuous Exploration using YOLO.
CVPR Workshop on Continuous and Open-Set Learning (CVPR-WS). 2017. Poster presentation and extended abstract
[bibtex] [abstract]
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]
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:
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]
2014
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]
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]
2012
Alexander Freytag, Erik Rodner, Paul Bodesheim, Joachim Denzler:
Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels.
Asian Conference on Computer Vision (ACCV). Pages 511-524. 2012. Best Paper Honorable Mention Award
[bibtex] [pdf] [web] [doi] [presentation] [abstract]