Search Results for author: Gernot A. Fink

Found 15 papers, 2 papers with code

Recognition-free Question Answering on Handwritten Document Collections

no code implementations12 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.

Question Answering

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

no code implementations31 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).

OOD Detection

Human Activity Recognition using Attribute-Based Neural Networks and Context Information

no code implementations28 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.

Activity Recognition

Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation

1 code implementation14 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.

Dimensionality Reduction Image Retrieval +2

Annotation-free Learning of Deep Representations for Word Spotting using Synthetic Data and Self Labeling

no code implementations4 Mar 2020 Fabian Wolf, Gernot A. Fink

Word spotting is a popular tool for supporting the first exploration of historic, handwritten document collections.

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets

no code implementations26 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.

Expolring Architectures for CNN-Based Word Spotting

no code implementations28 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.

Learning Attribute Representation for Human Activity Recognition

no code implementations2 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.

Activity Recognition

Weakly Supervised Object Detection with Pointwise Mutual Information

no code implementations26 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.

Weakly Supervised Object Detection

Learning Deep Representations for Word Spotting Under Weak Supervision

no code implementations1 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.

Word Spotting In Handwritten Documents

Neuron Pruning for Compressing Deep Networks using Maxout Architectures

no code implementations21 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.

Face Verification Handwritten Digit Recognition

Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images

no code implementations29 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.

General Classification Image Classification

Optimistic and Pessimistic Neural Networks for Scene and Object Recognition

no code implementations26 Sep 2016 Rene Grzeszick, Sebastian Sudholt, Gernot A. Fink

A novel method for adjusting the network's predictions based on uncertainty information is introduced.

Object Recognition

Zero-shot object prediction using semantic scene knowledge

no code implementations27 Apr 2016 Rene Grzeszick, Gernot A. Fink

This work focuses on the semantic relations between scenes and objects for visual object recognition.

Object Recognition

PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents

1 code implementation1 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

Cannot find the paper you are looking for? You can Submit a new open access paper.