Publications

Active and Incremental Learning with Weak Supervision.
Clemens-Alexander Brust and Christoph Käding and Joachim Denzler.
Künstliche Intelligenz (KI). 2020. (accepted)
[bibtex] [pdf] [abstract]

Automated Polyp Differentiation on Coloscopic Data using Semantic Segmentation with CNNs.
Marie Arlt and Jack Peter and Sven Sickert and Clemens-Alexander Brust and Joachim Denzler and Andreas Stallmach.
Endoscopy. 51 (04): pages 4. 2019.
[bibtex] [web] [abstract]

Active Learning for Deep Object Detection.
Clemens-Alexander Brust and Christoph Käding and Joachim Denzler.
Computer Vision Theory and Applications (VISAPP). Pages 181-190. 2019.
[bibtex] [pdf] [abstract]

Integrating Domain Knowledge: Using Hierarchies to Improve Deep Classifiers.
Clemens-Alexander Brust and Joachim Denzler.
Asian Conference on Pattern Recognition (ACPR). 2019.
[bibtex] [pdf] [abstract]

Not just a Matter of Semantics: The Relationship between Visual Similarity and Semantic Similarity.
Clemens-Alexander Brust and Joachim Denzler.
German Conference on Pattern Recognition (GCPR). Pages 414-427. 2019.
[bibtex] [pdf] [abstract]

Registration of High Resolution Sar and Optical Satellite Imagery Using Fully Convolutional Networks.
Stefan Hoffmann and Clemens-Alexander Brust and Maha Shadaydeh and Joachim Denzler.
International Geoscience and Remote Sensing Symposium (IGARSS). Pages 5152-5155. 2019.
[bibtex] [pdf] [abstract]

Dataless Black-Box Model Comparison.
Christoph Theiß and Clemens-Alexander Brust and Joachim Denzler.
Pattern Recognition and Image Analysis (PRIA). 28 (4): pages 676-683. 2018. (also published at ICPRAI 2018)
[bibtex] [abstract]

Keeping the Human in the Loop: Towards Automatic Visual Monitoring in Biodiversity Research.
Joachim Denzler and Christoph Käding and Clemens-Alexander Brust.
International Conference on Ecological Informatics (ICEI). Pages 16. 2018.
[bibtex] [abstract]

Abstract: More and more methods in the area of biodiversity research grounds upon new opportunities arising from modern sensing devices that in principle make it possible to continuously record sensor data from the environment. However, these opportunities allow easy recording of huge amount of data, while its evaluation is difficult, if not impossible due to the enormous effort of manual inspection by the researchers. At the same time, we observe impressive results in computer vision and machine learning that are based on two major developments: firstly, the increased performance of hardware together with the advent of powerful graphical processing units applied in scientific computing. Secondly, the huge amount of, in part, annotated image data provided by today's generation of Facebook and Twitter users that are available easily over databases (e.g., Flickr) and/or search engines. However, for biodiversity applications appropriate data bases of annotated images are still missing. In this presentation we discuss already available methods from computer vision and machine learning together with upcoming challenges in automatic monitoring in biodiversity research. We argue that the key element towards success of any automatic method is the possibility to keep the human in the loop - either for correcting errors and improving the system's quality over time, for providing annotation data at moderate effort, or for acceptance and validation reasons. Thus, we summarize already existing techniques from active and life-long learning together with the enormous developments in automatic visual recognition during the past years. In addition, to allow detection of the unexpected such an automatic system must be capable to find anomalies or novel events in the data. We discuss a generic framework for automatic monitoring in biodiversity research which is the result of collaboration between computer scientists and ecologists of the past years. The key ingredients of such a framework are initial, generic classifier, for example, powerful deep learning architectures, active learning to reduce costly annotation effort by experts, fine-grained recognition to differentiate between visually very similar species, and efficient incremental update of the classifier's model over time. For most of these challenges, we present initial solutions in sample applications. The results comprise the automatic evaluation of images from camera traps, attribute estimation for species, as well as monitoring in-situ data in environmental science. Overall, we like to demonstrate the potentials and open issues in bringing together computer scientists and ecologist to open new research directions for either area.

Towards Automated Visual Monitoring of Individual Gorillas in the Wild.
Brust, Clemens-Alexander and Burghardt, Tilo and Groenenberg, Milou and Käding, Christoph and Kühl, Hjalmar and Manguette, Marie and Denzler, Joachim.
ICCV Workshop on Visual Wildlife Monitoring (ICCV-WS). Pages 2820-2830. 2017.
[bibtex] [pdf] [abstract]

You Have To Look More Than Once: Active and Continuous Exploration using YOLO.
Clemens-Alexander Brust and Christoph Käding and Joachim Denzler. (2017) Poster presentation and extended abstract
[bibtex] [abstract]

Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks.
Clemens-Alexander Brust and Sven Sickert and Marcel Simon and Erik Rodner and Joachim Denzler. (2016)
[bibtex] [pdf] [abstract]

Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding.
Clemens-Alexander Brust and Sven Sickert and Marcel Simon and Erik Rodner and Joachim Denzler.
Computer Vision Theory and Applications (VISAPP). Pages 510-517. 2015.
[bibtex] [pdf] [abstract]

Efficient Convolutional Patch Networks for Scene Understanding.
Clemens-Alexander Brust and Sven Sickert and Marcel Simon and Erik Rodner and Joachim Denzler. (2015) Poster presentation and extended abstract
[bibtex] [pdf] [abstract]