Search Results for author: Martin Thoma

Found 9 papers, 3 papers with code

The WiLI benchmark dataset for written language identification

4 code implementations23 Jan 2018 Martin Thoma

This paper describes the WiLI-2018 benchmark dataset for monolingual written natural language identification.

General Classification Language Identification

Analysis and Optimization of Convolutional Neural Network Architectures

1 code implementation31 Jul 2017 Martin Thoma

Other results, such as the positive impact of learned color transformation on the test accuracy could not be confirmed.

Data Augmentation Object Recognition +1

The HASYv2 dataset

3 code implementations29 Jan 2017 Martin Thoma

This paper describes the HASYv2 dataset.

General Classification

A Survey of Semantic Segmentation

no code implementations21 Feb 2016 Martin Thoma

This survey gives an overview over different techniques used for pixel-level semantic segmentation.

Segmentation Semantic Segmentation

Creativity in Machine Learning

no code implementations12 Jan 2016 Martin Thoma

Recent machine learning techniques can be modified to produce creative results.

BIG-bench Machine Learning

On-line Recognition of Handwritten Mathematical Symbols

no code implementations29 Nov 2015 Martin Thoma

Finding the name of an unknown symbol is often hard, but writing the symbol is easy.

Data Augmentation

Über die Klassifizierung von Knoten in dynamischen Netzwerken mit Inhalt

no code implementations23 Nov 2015 Martin Thoma

Die von Aggarwal und Li beschriebene experimentelle Analyse ergab, dass er auch auf dynamischen Graphen mit 19396 bzw.

Pixel-wise Segmentation of Street with Neural Networks

no code implementations2 Nov 2015 Sebastian Bittel, Vitali Kaiser, Marvin Teichmann, Martin Thoma

Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks.

Object Recognition regression +1

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