162 citations · 1.2k across the 78 of their papers we have counts for
9 papers · 1 filter
A Pitfall of Unsupervised Pre-Training
Michele Alberti, Mathias Seuret, Rolf Ingold +1
The point of this paper is to question typical assumptions in deep learning and suggest alternatives. A particular contribution is to prove that even if a Stacked Convolutional Aut…
Open Evaluation Tool for Layout Analysis of Document Images
Michele Alberti, Manuel Bouillon, Rolf Ingold +1
This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level. We introduce a new evaluation tool that is…
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines
Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke +1
This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)effic…
Historical Document Image Segmentation with LDA-Initialized Deep Neural Networks
Michele Alberti, Mathias Seuret, Vinaychandran Pondenkandath +2
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a de…
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification
Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed +1
We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error b…
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
Ayushman Dash, John Cristian Borges Gamboa, Sheraz Ahmed +2
In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Generative Adversarial Network (GAN) for synthesizing i…