21 citations · 21 across the 2 of their papers we have counts for
7 papers · 1 filter
Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge
Clemens-Alexander Brust, Björn Barz, Joachim Denzler
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…
Active and Incremental Learning with Weak Supervision
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler
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 benc…
Integrating domain knowledge: using hierarchies to improve deep classifiers
Clemens-Alexander Brust, Joachim Denzler
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 s…
Not just a matter of semantics: the relationship between visual similarity and semantic similarity
Clemens-Alexander Brust, Joachim Denzler
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 t…
Active Learning for Deep Object Detection
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler
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…
Neither Quick Nor Proper -- Evaluation of QuickProp for Learning Deep Neural Networks
Clemens-Alexander Brust, Sven Sickert, Marcel Simon +2
Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have…