1 code implementation • 1 Apr 2016 • Sebastian Sudholt, Gernot A. Fink
In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation.
General Classification Word Spotting In Handwritten Documents
no code implementations • 27 Apr 2016 • Rene Grzeszick, Gernot A. Fink
This work focuses on the semantic relations between scenes and objects for visual object recognition.
no code implementations • 26 Sep 2016 • Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink
A novel method for adjusting the network's predictions based on uncertainty information is introduced.
no code implementations • 29 Jun 2017 • Waleed M. Gondal, Jan M. Köhler, René Grzeszick, Gernot A. Fink, Michael Hirsch
Although these approaches could help to build trust in the CNNs predictions, they are only slightly shown to work with medical image data which often poses a challenge as the decision for a class relies on different lesion areas scattered around the entire image.
no code implementations • 21 Jul 2017 • Fernando Moya Rueda, Rene Grzeszick, Gernot A. Fink
Furthermore, it will be shown that neuron pruning can be combined with subsequent weight pruning, reducing the size of the LeNet-5 and VGG16 up to $92\%$ and $80\%$ respectively.
no code implementations • 1 Dec 2017 • Neha Gurjar, Sebastian Sudholt, Gernot A. Fink
Convolutional Neural Networks have made their mark in various fields of computer vision in recent years.
no code implementations • 26 Jan 2018 • Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink
It is shown that the combination of pointwise mutual information and a cosine loss eases the learning process and thus improves the accuracy.
no code implementations • 2 Feb 2018 • Fernando Moya Rueda, Gernot A. Fink
Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets.
no code implementations • 28 Jun 2018 • Eugen Rusakov, Sebastian Sudholt, Fabian Wolf, Gernot A. Fink
The goal in word spotting is to retrieve parts of document images which are relevant with respect to a certain user-defined query.
no code implementations • 26 Mar 2019 • Fabian Wolf, Philipp Oberdiek, Gernot A. Fink
In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting.
no code implementations • 4 Mar 2020 • Fabian Wolf, Gernot A. Fink
Word spotting is a popular tool for supporting the first exploration of historic, handwritten document collections.
1 code implementation • 14 May 2020 • Philipp Oberdiek, Matthias Rottmann, Gernot A. Fink
When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts.
no code implementations • 28 Oct 2021 • Stefan Lüdtke, Fernando Moya Rueda, Waqas Ahmed, Gernot A. Fink, Thomas Kirste
Here, we show how such context information can be integrated systematically into a deep neural network-based HAR system.
1 code implementation • 31 Jan 2022 • Philipp Oberdiek, Gernot A. Fink, Matthias Rottmann
We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs).
Out of Distribution (OOD) Detection Uncertainty Quantification
no code implementations • 12 Feb 2022 • Oliver Tüselmann, Friedrich Müller, Fabian Wolf, Gernot A. Fink
In recent years, considerable progress has been made in the research area of Question Answering (QA) on document images.
no code implementations • 7 Jun 2022 • Fabian Wolf, Gernot A. Fink
Performances of Handwritten Text Recognition (HTR) models are largely determined by the availability of labeled and representative training samples.
no code implementations • 2 Dec 2022 • Shrutarv Awasthi, Fernando Moya Rueda, Gernot A. Fink
HAR is challenging due to the inter and intra-variance of human movements; moreover, annotated datasets from on-body devices are scarce.
no code implementations • 19 Jan 2023 • Nilah Ravi Nair, Lena Schmid, Fernando Moya Rueda, Markus Pauly, Gernot A. Fink, Christopher Reining
It is unknown what physical characteristics and/or soft-biometrics, such as age, height, and weight, need to be taken into account to train a classifier to achieve robustness towards heterogeneous populations in the training and testing data.
no code implementations • 4 Apr 2023 • Nilah Ravi Nair, Fernando Moya Rueda, Christopher Reining, Gernot A. Fink
On-body device (OBD) recordings of human movements are often preferred for HAR applications not only for their reliability but as an approach for identity protection, e. g., in industrial settings.