I am a professor for machine learning, data science, and industrial IoT at University of Applied Sciences Berlin. My research activities span areas such as learning with limited data, building robust visual recognition models for quality control and medical image analysis, as well as combining annotation and learning workflows.

Previously, I was leading the machine learning team at the corporate research department of the ZEISS Group develop machine learning solutions for a wide range of products. Furthermore, I have been a lecturer in the computer vision group at the Friedrich Schiller University of Jena (Germany) leading the machine learning research activities and I worked as a PostDoc in the computer vision group of Trevor Darrell at ICSI/EECS (UC Berkeley, California).

Research areas

Learning with limited data

Active and Adaptive Learning, Novelty Detection

Robust Visual Recognition

Detection, Uncertainty Estimation for Vision Models

Medical Vision

Medical Vision Applications, Microscopy, Video Analysis

Quality Control in Production

Data Analysis in Production, Visual Inspection

Recent and selected publications

2020

The whole is more than its parts? From explicit to implicit pose normalization.
Marcel Simon and Erik Rodner and Trevor Darell and Joachim Denzler.
IEEE Transactions on Pattern Analysis and Machine Intelligence. 42(3): 749-763. 2020. BibTeX pdf more ...

Abstract: Fine-grained classification describes the automated recognition of visually similar object categories like birds species. Previous works were usually based on explicit pose normalization, i.e., the detection and description of object parts. However, recent models based on a final global average or bilinear pooling have achieved a comparable accuracy without this concept. In this paper, we analyze the advantages of these approaches over generic CNNs and explicit pose normalization approaches. We also show how they can achieve an implicit normalization of the object pose. A novel visualization technique called activation flow is introduced to investigate limitations in pose handling in traditional CNNs like AlexNet and VGG. Afterward, we present and compare the explicit pose normalization approach neural activation constellations and a generalized framework for the final global average and bilinear pooling called -pooling. We observe that the latter often achieves a higher accuracy improving common CNN models by up to 22.9%, but lacks the interpretability of the explicit approaches. We present a visualization approach for understanding and analyzing predictions of the model to address this issue. Furthermore, we show that our approaches for fine-grained recognition are beneficial for other fields like action recognition.

2019

Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection.
Björn Barz and Erik Rodner and Yanira Guanche Garcia and Joachim Denzler.
IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(5): 1088-1101. 2019. (Pre-print published in 2018.) BibTeX pdf www code more ...

Abstract: Automatic detection of anomalies in space- and time-varying measurements is an important tool in several fields, e.g., fraud detection, climate analysis, or healthcare monitoring. We present an algorithm for detecting anomalous regions in multivariate spatio-temporal time-series, which allows for spotting the interesting parts in large amounts of data, including video and text data. In opposition to existing techniques for detecting isolated anomalous data points, we propose the "Maximally Divergent Intervals" (MDI) framework for unsupervised detection of coherent spatial regions and time intervals characterized by a high Kullback-Leibler divergence compared with all other data given. In this regard, we define an unbiased Kullback-Leibler divergence that allows for ranking regions of different size and show how to enable the algorithm to run on large-scale data sets in reasonable time using an interval proposal technique. Experiments on both synthetic and real data from various domains, such as climate analysis, video surveillance, and text forensics, demonstrate that our method is widely applicable and a valuable tool for finding interesting events in different types of data.
Fully Convolutional Networks in Multimodal Nonlinear Microscopy Images for Automated Detection of Head and Neck Carcinoma: A Pilot Study.
Erik Rodner and Thomas Bocklitz and Ferdinand von Eggeling and Günther Ernst and Olga Chernavskaia and Jürgen Popp and Joachim Denzler and Orlando Guntinas-Lichius.
Head and Neck. 41(1): 116-121. 2019. BibTeX www more ...

Abstract: A fully convolutional neural networks (FCN)-based automated image analysis algorithm to discriminate between head and neck cancer and noncancerous epithelium based on nonlinear microscopic images was developed. Head and neck cancer sections were used for standard histopathology and co-registered with multimodal images from the same sections using the combination of coherent anti-Stokes Raman scattering, two-photon excited fluorescence, and second harmonic generation microscopy. The images analyzed with semantic segmentation using a FCN for four classes: cancer, normal epithelium, background, and other tissue types. A total of 114 images of 12 patients were analyzed. Using a patch score aggregation, the average recognition rate and an overall recognition rate or the four classes were 88.9\% and 86.7\%, respectively. A total of 113seconds were needed to process a whole-slice image in the dataset. Multimodal nonlinear microscopy in combination with automated image analysis using FCN seems to be a promising technique for objective differentiation between head and neck cancer and noncancerous epithelium.

2018

Active Learning for Regression Tasks with Expected Model Output Changes.
Christoph Käding and Erik Rodner and Alexander Freytag and Oliver Mothes and Björn Barz and Joachim Denzler.
British Machine Vision Conference (BMVC). 2018. BibTeX pdf code more ...

Abstract: Annotated training data is the enabler for supervised learning. While recording data at large scale is possible in some application domains, collecting reliable annotations is time-consuming, costly, and often a project's bottleneck. Active learning aims at reducing the annotation effort. While this field has been studied extensively for classification tasks, it has received less attention for regression problems although the annotation cost is often even higher. We aim at closing this gap and propose an active learning approach to enable regression applications. To address continuous outputs, we build on Gaussian process models -- an established tool to tackle even non-linear regression problems. For active learning, we extend the expected model output change (EMOC) framework to continuous label spaces and show that the involved marginalizations can be solved in closed-form. This mitigates one of the major drawbacks of the EMOC principle. We empirically analyze our approach in a variety of application scenarios. In summary, we observe that our approach can efficiently guide the annotation process and leads to better models in shorter time and at lower costs.
HER2 challenge contest: a detailed assessment of automated HER2 scoring algorithms in whole slide images of breast cancer tissues.
Talha Qaiser and Abhik Mukherjee and Chaitanya Reddy PB and Sai D Munugoti and Vamsi Tallam and Tomi Pitkaho and Taina Lehtimki and Thomas Naughton and Matt Berseth and Anbal Pedraza and Ramakrishnan Mukundan and Matthew Smith and Abhir Bhalerao and Erik Rodner and Marcel Simon and Joachim Denzler and Chao-Hui Huang and Gloria Bueno and David Snead and Ian O Ellis and Mohammad Ilyas and Nasir Rajpoot.
Histopathology. 72(2): 227-238. 2018. BibTeX www more ...

Abstract: Aims Evaluating expression of the human epidermal growth factor receptor 2 (HER2) by visual examination of immunohistochemistry (IHC) on invasive breast cancer (BCa) is a key part of the diagnostic assessment of BCa due to its recognized importance as a predictive and prognostic marker in clinical practice. However, visual scoring of HER2 is subjective, and consequently prone to interobserver variability. Given the prognostic and therapeutic implications of HER2 scoring, a more objective method is required. In this paper, we report on a recent automated HER2 scoring contest, held in conjunction with the annual PathSoc meeting held in Nottingham in June 2016, aimed at systematically comparing and advancing the state-of-the-art artificial intelligence (AI)-based automated methods for HER2 scoring. Methods and results The contest data set comprised digitized whole slide images (WSI) of sections from 86 cases of invasive breast carcinoma stained with both haematoxylin and eosin (H&E) and IHC for HER2. The contesting algorithms predicted scores of the IHC slides automatically for an unseen subset of the data set and the predicted scores were compared with the ground truth (a consensus score from at least two experts). We also report on a simple Man versus Machine contest for the scoring of HER2 and show that the automated methods could beat the pathology experts on this contest data set. Conclusions This paper presents a benchmark for comparing the performance of automated algorithms for scoring of HER2. It also demonstrates the enormous potential of automated algorithms in assisting the pathologist with objective IHC scoring.

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 Neumann and Florian Stelzle and Andreas Maier.
Scientific Reports. 7(1): 41598-017. 2017. BibTeX www
Large-Scale Gaussian Process Inference with Generalized Histogram Intersection Kernels for Visual Recognition Tasks.
Erik Rodner and Alexander Freytag and Paul Bodesheim and Björn Fröhlich and Joachim Denzler.
International Journal of Computer Vision (IJCV). 121(2): 253-280. 2017. BibTeX pdf www
Fast Learning and Prediction for Object Detection using Whitened CNN Features.
Björn Barz and Erik Rodner and Christoph Käding and Joachim Denzler.
arXiv preprint arXiv:1704.02930. 2017. BibTeX www
Generalized orderless pooling performs implicit salient matching.
Marcel Simon and Yang Gao and Trevor Darrell and Joachim Denzler and Erik Rodner.
International Conference on Computer Vision (ICCV). 4970-4979. 2017. BibTeX pdf

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 more ...

Abstract: The revival of deep neural networks and the availability of ImageNet laid the foundation for recent success in highly complex recognition tasks. However, ImageNet does not cover all visual concepts of all possible application scenarios. Hence, application experts still record new data constantly and expect the data to be used upon its availability. In this paper, we follow this observation and apply the classical concept of fine-tuning deep neural networks to scenarios where data from known or completely new classes is continuously added. Besides a straightforward realization of continuous fine-tuning, we empirically analyze how computational burdens of training can be further reduced. Finally, we visualize how the networks attention maps evolve over time which allows for visually investigating what the network learned during continuous fine-tuning.
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.
Maximally Divergent Intervals for Anomaly Detection.
Erik Rodner and Björn Barz and Yanira Guanche and Milan Flach and Miguel Mahecha and Paul Bodesheim and Markus Reichstein and Joachim Denzler.
ICML Workshop on Anomaly Detection (ICML-WS). 2016. Best Paper Award BibTeX pdf code
Large-scale Active Learning with Approximated Expected Model Output Changes.
Christoph Käding and Alexander Freytag and Erik Rodner and Andrea Perino and Joachim Denzler.
German Conference on Pattern Recognition (GCPR). 179-191. 2016. BibTeX pdf www code supplementary more ...

Abstract: Incremental learning of visual concepts is one step towards reaching human capabilities beyond closed-world assumptions. Besides recent progress, it remains one of the fundamental challenges in computer vision and machine learning. Along that path, techniques are needed which allow for actively selecting informative examples from a huge pool of unlabeled images to be annotated by application experts. Whereas a manifold of active learning techniques exists, they commonly suffer from one of two drawbacks: (i) either they do not work reliably on challenging real-world data or (ii) they are kernel-based and not scalable with the magnitudes of data current vision applications need to deal with. Therefore, we present an active learning and discovery approach which can deal with huge collections of unlabeled real-world data. Our approach is based on the expected model output change principle and overcomes previous scalability issues. We present experiments on the large-scale MS-COCO dataset and on a dataset provided by biodiversity researchers. Obtained results reveal that our technique clearly improves accuracy after just a few annotations. At the same time, it outperforms previous active learning approaches in academic and real-world scenarios.
Chimpanzee Faces in the Wild: Log-Euclidean CNNs for Predicting Identities and Attributes of Primates.
Alexander Freytag and Erik Rodner and Marcel Simon and Alexander Loos and Hjalmar Kühl and Joachim Denzler.
German Conference on Pattern Recognition (GCPR). 51-63. 2016. BibTeX pdf www supplementary more ...

Abstract: In this paper, we investigate how to predict attributes of chimpanzees such as identity, age, age group, and gender. We build on convolutional neural networks, which lead to significantly superior results compared with previous state-of-the-art on hand-crafted recognition pipelines. In addition, we show how to further increase discrimination abilities of CNN activations by the Log-Euclidean framework on top of bilinear pooling. We finally introduce two curated datasets consisting of chimpanzee faces with detailed meta-information to stimulate further research. Our results can serve as the foundation for automated large-scale animal monitoring and analysis.
Convolutional Neural Networks as a Computational Model for the Underlying Processes of Aesthetics Perception.
Joachim Denzler and Erik Rodner and Marcel Simon.
ECCV Workshop on Computer Vision for Art Analysis. 2016. BibTeX pdf www
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 more ...

Abstract: The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet. In consequence, we need curious and continuously learning algorithms that actively acquire knowledge about semantic concepts which are present in available unlabeled data. As a step towards this goal, we show how to perform continuous active learning and exploration, where an algorithm actively selects relevant batches of unlabeled examples for annotation. These examples could either belong to already known or to yet undiscovered classes. Our algorithm is based on a new generalization of the Expected Model Output Change principle for deep architectures and is especially tailored to deep neural networks. Furthermore, we show easy-to-implement approximations that yield efficient techniques for active selection. Empirical experiments show that our method outperforms currently used heuristics.