Clemens-Alexander Brust

Clemens-Alexander Brust
German Aerospace Center (DLR) | DLR · Institut für Datenwissenschaften

Dr. rer. nat.
Secure Software Engineering @ DLR Data Science

About

26
Publications
6,482
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
289
Citations
Additional affiliations
March 2017 - present
Friedrich Schiller University Jena
Position
  • Research Associate
November 2014 - July 2016
Friedrich Schiller University Jena
Position
  • Research Assistant
Education
April 2015 - February 2017
Friedrich Schiller University Jena
Field of study
  • Computational Science
October 2010 - October 2014
Friedrich Schiller University Jena
Field of study
  • Computer Science

Publications

Publications (26)
Preprint
Full-text available
Automatic vulnerability detection on C/C++ source code has benefitted from the introduction of machine learning to the field, with many recent publications considering this combination. In contrast, assembly language or machine code artifacts receive little attention, although there are compelling reasons to study them. They are more representative...
Article
Animal re-identification based on image data, either recorded manually by photographers or automatically with camera traps, is an important task for ecological studies about biodiversity and conservation that can be highly automatized with algorithms from computer vision and machine learning. However, fixed identification models only trained with s...
Thesis
Full-text available
Low availability of labeled training data often poses a fundamental limit to the accuracy of computer vision applications using machine learning methods. While these methods are improved continuously, e.g., through better neural network architectures, there cannot be a single methodical change that increases the accuracy on all possible tasks. This...
Code
Source code and data for "ROMEO: Exploring Juliet through the Lens of Assembly Language"
Preprint
Full-text available
Learning from imprecise labels such as "animal" or "bird", but making precise predictions like "snow bunting" at test time is an important capability when expertly labeled training data is scarce. Contributions by volunteers or results of web crawling lack precision in this manner, but are still valuable. And crucially, these weakly labeled example...
Chapter
Uncertainty sampling is a widely used active learning strategy to select unlabeled examples for annotation. However, previous work hints at weaknesses of uncertainty sampling when combined with deep learning, where the amount of data is even more significant. To investigate these problems, we analyze the properties of the latent statistical estimat...
Preprint
Full-text available
Noisy data, crawled from the web or supplied by volunteers such as Mechanical Turkers or citizen scientists, is considered an alternative to professionally labeled data. There has been research focused on mitigating the effects of label noise. It is typically modeled as inaccuracy, where the correct label is replaced by an incorrect label from the...
Chapter
One of the most prominent problems in machine learning in the age of deep learning is the availability of sufficiently large annotated datasets. For specific domains, e.g. animal species, a long-tail distribution means that some classes are observed and annotated insufficiently. Additional labels can be prohibitively expensive, e.g. because domain...
Preprint
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only a...
Article
Full-text available
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only a...
Article
Full-text available
One of the most prominent problems in machine learning in the age of deep learning is the availability of sufficiently large annotated datasets. For specific domains, e.g. animal species, a long-tail distribution means that some classes are observed and annotated insufficiently. Additional labels can be prohibitively expensive, e.g. because domain...
Chapter
Knowledge transfer, zero-shot learning and semantic image retrieval are methods that aim at improving accuracy by utilizing semantic information, e.g., from WordNet. It is assumed that this information can augment or replace missing visual data in the form of labeled training images because semantic similarity correlates with visual similarity. Thi...
Conference Paper
Full-text available
The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, wh...
Preprint
Full-text available
Knowledge transfer, zero-shot learning and semantic image retrieval are methods that aim at improving accuracy by utilizing semantic information, e.g. from WordNet. It is assumed that this information can augment or replace missing visual data in the form of labeled training images because semantic similarity somewhat aligns with visual similarity....
Preprint
Full-text available
One of the most prominent problems in machine learning in the age of deep learning is the availability of sufficiently large annotated datasets. While for standard problem domains (ImageNet classification), appropriate datasets exist, for specific domains, \eg classification of animal species, a long-tail distribution means that some classes are ob...
Article
In a time where the training of new machine learning models is extremely time-consuming and resource-intensive and the sale of these models or the access to them is more popular than ever, it is important to think about ways to ensure the protection of these models against theft. In this paper, we present a method for estimating the similarity or d...
Preprint
Full-text available
The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, wh...
Preprint
Full-text available
Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neura...
Article
Full-text available
Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neura...
Conference Paper
Full-text available
In this paper, we present convolutional patch networks, which are convolutional (neural) networks (CNN) learned to distinguish different image patches and which can be used for pixel-wise labeling. We show how to easily learn spatial priors for certain categories jointly with their appearance. Experiments for urban scene understanding demonstrate s...
Conference Paper
Full-text available
Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial in...

Network

Cited By

Projects

Projects (5)
Project
Explore the advantages of a binary code representation for vulnerability detection, compared to source code or other alternatives.
Archived project
Active Learning for Deep Object Detection
Archived project
The Visual-Semantic Intersection