research
∙
06/07/2022
CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness
We present CAISAR, an open-source platform under active development for ...
share
research
∙
03/15/2021
Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs
We present a framework to generate synthetic historical documents with p...
research
∙
06/11/2019
Improving Reproducible Deep Learning Workflows with DeepDIVA
The field of deep learning is experiencing a trend towards producing rep...
research
∙
06/11/2019
Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass
In the last decades we have witnessed the success of applications of Art...
research
∙
05/22/2019
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
Automatic analysis of scanned historical documents comprises a wide rang...
research
∙
11/05/2018
Leveraging Random Label Memorization for Unsupervised Pre-Training
We present a novel approach to leverage large unlabeled datasets by pre-...
research
∙
10/17/2018
Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks
Biometric authentication by means of handwritten signatures is a challen...
research
∙
08/21/2018
Are You Tampering With My Data?
We propose a novel approach towards adversarial attacks on neural networ...
research
∙
04/23/2018
DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
We introduce DeepDIVA: an infrastructure designed to enable quick and in...
research
∙
04/05/2018
Identifying Cross-Depicted Historical Motifs
Cross-depiction is the problem of identifying the same object even when ...
research
∙
11/23/2017
Open Evaluation Tool for Layout Analysis of Document Images
This paper presents an open tool for standardizing the evaluation proces...
research
∙
11/23/2017
A Pitfall of Unsupervised Pre-Training
The point of this paper is to question typical assumptions in deep learn...
research
∙
10/19/2017
Historical Document Image Segmentation with LDA-Initialized Deep Neural Networks
In this paper, we present a novel approach to perform deep neural networ...
research
∙
09/05/2017
Context Generation from Formal Specifications for C Analysis Tools
Analysis tools like abstract interpreters, symbolic execution tools and ...
research
∙
03/13/2017
What You Expect is NOT What You Get! Questioning Reconstruction/Classification Correlation of Stacked Convolutional Auto-Encoder Features
In this paper, we thoroughly investigate the quality of features produce...
research
∙
02/01/2017