no code implementations • 7 Jun 2022 • Julien Girard-Satabin, Michele Alberti, François Bobot, Zakaria Chihani, Augustin Lemesle
We present CAISAR, an open-source platform under active development for the characterization of AI systems' robustness and safety.
1 code implementation • 15 Mar 2021 • Lars Vögtlin, Manuel Drazyk, Vinaychandran Pondenkandath, Michele Alberti, Rolf Ingold
Second, we transfer the style of a collection of unlabeled historical images to these template documents while preserving their text and layout.
Optical Character Recognition (OCR) Synthetic Data Generation
2 code implementations • 12 Nov 2019 • Michele Alberti, Angela Botros, Narayan Schuez, Rolf Ingold, Marcus Liwicki, Mathias Seuret
In this work, we investigate the application of trainable and spectrally initializable matrix transformations on the feature maps produced by convolution operations.
no code implementations • 11 Jun 2019 • Michele Alberti, Vinaychandran Pondenkandath, Lars Vögtlin, Marcel Würsch, Rolf Ingold, Marcus Liwicki
The field of deep learning is experiencing a trend towards producing reproducible research.
2 code implementations • 11 Jun 2019 • Joel Niklaus, Michele Alberti, Vinaychandran Pondenkandath, Rolf Ingold, Marcus Liwicki
Jass is a very popular card game in Switzerland and is closely connected with Swiss culture.
1 code implementation • 11 Jun 2019 • Michele Alberti, Lars Vögtlin, Vinaychandran Pondenkandath, Mathias Seuret, Rolf Ingold, Marcus Liwicki
We measured the performance of our method on a recent dataset of challenging medieval manuscripts and surpassed state-of-the-art results by reducing the error by 80. 7%.
Ranked #1 on Text-Line Extraction on DIVA-HisDB
no code implementations • 22 May 2019 • Linda Studer, Michele Alberti, Vinaychandran Pondenkandath, Pinar Goktepe, Thomas Kolonko, Andreas Fischer, Marcus Liwicki, Rolf Ingold
Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples.
Ranked #7 on Image Classification on Kuzushiji-MNIST
no code implementations • 5 Nov 2018 • Vinaychandran Pondenkandath, Michele Alberti, Sammer Puran, Rolf Ingold, Marcus Liwicki
We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets.
1 code implementation • 17 Oct 2018 • Paul Maergner, Vinaychandran Pondenkandath, Michele Alberti, Marcus Liwicki, Kaspar Riesen, Rolf Ingold, Andreas Fischer
Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures.
1 code implementation • 21 Aug 2018 • Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch, Manuel Bouillon, Mathias Seuret, Rolf Ingold, Marcus Liwicki
We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models.
12 code implementations • 23 Apr 2018 • Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch, Rolf Ingold, Marcus Liwicki
We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality.
no code implementations • 5 Apr 2018 • Vinaychandran Pondenkandath, Michele Alberti, Nicole Eichenberger, Rolf Ingold, Marcus Liwicki
Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners.
1 code implementation • 23 Nov 2017 • Michele Alberti, Manuel Bouillon, Rolf Ingold, Marcus Liwicki
This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level.
no code implementations • 23 Nov 2017 • Michele Alberti, Mathias Seuret, Rolf Ingold, Marcus Liwicki
Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.
1 code implementation • 19 Oct 2017 • Michele Alberti, Mathias Seuret, Vinaychandran Pondenkandath, Rolf Ingold, Marcus Liwicki
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA).
no code implementations • 13 Mar 2017 • Michele Alberti, Mathias Seuret, Rolf Ingold, Marcus Liwicki
Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.
no code implementations • 1 Feb 2017 • Mathias Seuret, Michele Alberti, Rolf Ingold, Marcus Liwicki
In this paper, we present a novel approach for initializing deep neural networks, i. e., by turning PCA into neural layers.