In this area of research, I am particularly interested in learning representations of visual data by directly optimizing with respect to a performance objective. In general, we try to step away from hand-crafted features and rather design complex parameterized models that can be learned from data.

2017

Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning.
Marc Aubreville and Christian Knipfer and Nicolai Oetter and Christian Jaremenko and Erik Rodner and Joachim Denzler and Christopher Bohr and Helmut Neumannt and Florian Stelzle and Andreas Maier.
arXiv preprint arXiv:1703.01622. 2017. BibTeX www

2016

Fine-tuning Deep Neural Networks in Continuous Learning Scenarios.
Christoph Käding and Erik Rodner and Alexander Freytag and Joachim Denzler.
ACCV Workshop on Interpretation and Visualization of Deep Neural Nets (ACCV-WS). 2016. BibTeX pdf www supplementary
Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches.
Erik Rodner and Marcel Simon and Bob Fisher and Joachim Denzler.
British Machine Vision Conference (BMVC). 2016. BibTeX pdf supplementary
Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets.
Manuel Amthor and Erik Rodner and Joachim Denzler.
British Machine Vision Conference (BMVC). 2016. BibTeX pdf
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.
arXiv preprint arXiv:1606.04333. 2016. BibTeX pdf www more ...

Abstract: Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp during learning and testing of fully convolutional networks for the task of semantic segmentation. We compare QuickProp empirically with gradient descent, which is the current standard method. Experiments suggest that QuickProp can not compete with standard gradient descent techniques for complex computer vision tasks like semantic segmentation.
Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes.
Christoph Käding and Erik Rodner and Alexander Freytag and Joachim Denzler.
NIPS Workshop on Continual Learning and Deep Networks (NIPS-WS). 2016. BibTeX pdf www

2015

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks.
Marcel Simon and Erik Rodner.
International Conference on Computer Vision (ICCV). 2015. BibTeX pdf www more ...

Abstract: Part models of object categories are essential for challenging recognition tasks, where differences in categories are subtle and only reflected in appearances of small parts of the object. We present an approach that is able to learn part models in a completely unsupervised manner, without part annotations and even without given bounding boxes during learning. The key idea is to find constellations of neural activation patterns computed using convolutional neural networks. In our experiments, we outperform existing approaches for fine-grained recognition on the CUB200-2011, Oxford PETS, and Oxford Flowers dataset in case no part or bounding box annotations are available and achieve state-of-the-art performance for the Stanford Dog dataset. We also show the benefits of neural constellation models as a data augmentation technique for fine-tuning. Furthermore, our paper unites the areas of generic and fine-grained classification, since our approach is suitable for both scenarios.
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.
International Conference on Computer Vision Theory and Applications (VISAPP). 510-517. 2015. BibTeX pdf www code more ...

Abstract: Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset. Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.
Efficient Convolutional Patch Networks for Scene Understanding.
Clemens-Alexander Brust and Sven Sickert and Marcel Simon and Erik Rodner and Joachim Denzler.
CVPR Workshop on Scene Understanding (CVPR-WS). 2015. BibTeX pdf code presentation more ...

Abstract: In this paper, we present convolutional patch networks, which are convolutional (neural) networks (CNN) learned to distinguish different image patches and which can be used for pixel-wise labeling. We show how to easily learn spatial priors for certain categories jointly with their appearance. Experiments for urban scene understanding demonstrate state-of-the-art results on the LabelMeFacade dataset. Our approach is implemented as a new CNN framework especially designed for semantic segmentation with fully-convolutional architectures.
Fine-grained Recognition Datasets for Biodiversity Analysis.
Erik Rodner and Marcel Simon and Gunnar Brehm and Stephanie Pietsch and J. Wolfgang Wägele and Joachim Denzler.
CVPR Workshop on Fine-grained Visual Classification (CVPR-WS). 2015. BibTeX pdf www
Understanding Object Descriptions in Robotics by Open-vocabulary Object Retrieval and Detection.
Sergio Guadarrama and Erik Rodner and Kate Saenko and Trevor Darrell.
International Journal of Robotics Research (IJRR). 35(1-3): 265-280. 2015. BibTeX pdf www

2014

Open-vocabulary Object Retrieval.
Sergio Guadarrama and Erik Rodner and Kate Saenko and Ning Zhang and Ryan Farrell and Jeff Donahue and Trevor Darrell.
Robotics Science and Systems (RSS). 41, ISBN 978-0-9923747-0-9. 2014. Awarded with an AAAI invited talk BibTeX pdf www more ...

Abstract: In this paper, we address the problem of retrieving objects based on open-vocabulary natural language queries: Given a phrase describing a specific object, e.g., the corn flakes box, the task is to find the best match in a set of images containing candidate objects. When naming objects, humans tend to use natural language with rich semantics, including basic-level categories, fine-grained categories, and instance-level concepts such as brand names. Existing approaches to large-scale object recognition fail in this scenario, as they expect queries that map directly to a fixed set of pre-trained visual categories, e.g. ImageNet synset tags. We address this limitation by introducing a novel object retrieval method. Given a candidate object image, we first map it to a set of words that are likely to describe it, using several learned image-to-text projections. We also propose a method for handling open-vocabularies, i.e., words not contained in the training data. We then compare the natural language query to the sets of words predicted for each candidate and select the best match. Our method can combine category- and instance-level semantics in a common representation. We present extensive experimental results on several datasets using both instance-level and category-level matching and show that our approach can accurately retrieve objects based on extremely varied open-vocabulary queries. The source code of our approach will be publicly available together with pre-trained models and could be directly used for robotics applications.
Exemplar-specific Patch Features for Fine-grained Recognition.
Alexander Freytag and Erik Rodner and Trevor Darrell and Joachim Denzler.
German Conference on Pattern Recognition (GCPR). 144-156. 2014. BibTeX pdf code supplementary more ...

Abstract: In this paper, we present a new approach for fine-grained recognition or subordinate categorization, tasks where an algorithm needs to reliably differentiate between visually similar categories, e.g. different bird species. While previous approaches aim at learning a single generic representation and models with increasing complexity, we propose an orthogonal approach that learns patch representations specifically tailored to every single test exemplar. Since we query a constant number of images similar to a given test image, we obtain very compact features and avoid large-scale training with all classes and examples. Our learned mid-level features are build on shape and color detectors estimated from discovered patches reflecting small highly discriminative structures in the queried images. We evaluate our approach for fine-grained recognition on the CUB-2011 birds dataset and show that high recognition rates can be obtained by model combination.
Part Detector Discovery in Deep Convolutional Neural Networks.
Marcel Simon and Erik Rodner and Joachim Denzler.
Asian Conference on Computer Vision (ACCV). 162-177. 2014. BibTeX pdf code more ...

Abstract: Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large variation of appearance and pose. In this paper, we show how pre-trained convolutional neural networks can be used for robust and efficient object part discovery and localization without the necessity to actually train the network on the current dataset. Our approach called part detector discovery (PDD) is based on analyzing the gradient maps of the network outputs and finding activation centers spatially related to annotated semantic parts or bounding boxes. This allows us not just to obtain excellent performance on the CUB200-2011 dataset, but in contrast to previous approaches also to perform detection and bird classification jointly without requiring a given bounding box annotation during testing and ground-truth parts during training.
Part Localization by Exploiting Deep Convolutional Networks.
Marcel Simon and Erik Rodner and Joachim Denzler.
ECCV Workshop on Parts and Attributes (ECCV-WS). 2014. BibTeX pdf www
Birds of a Feather Flock Together - Local Learning of Mid-level Representations for Fine-grained Recognition.
Alexander Freytag and Erik Rodner and Joachim Denzler.
ECCV Workshop on Parts and Attributes (ECCV-WS). 2014. BibTeX pdf www code presentation