2 citations · 2 across the 4 of their papers we have counts for
7 papers
InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images
Konstantin Kobs, Michael Steininger, Andreas Hotho
Common Deep Metric Learning (DML) datasets specify only one notion of similarity, e.g., two images in the Cars196 dataset are deemed similar if they show the same car model. We arg…
On Background Bias in Deep Metric Learning
Konstantin Kobs, Andreas Hotho
Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images. When us…
Do Different Deep Metric Learning Losses Lead to Similar Learned Features?
Konstantin Kobs, Michael Steininger, Andrzej Dulny +1
Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected resu…
NICER: Aesthetic Image Enhancement with Humans in the Loop
Michael Fischer, Konstantin Kobs, Andreas Hotho
Fully- or semi-automatic image enhancement software helps users to increase the visual appeal of photos and does not require in-depth knowledge of manual image editing. However, fu…
Anomaly Detection in Beehives using Deep Recurrent Autoencoders
Padraig Davidson, Michael Steininger, Florian Lautenschlager +3
Precision beekeeping allows to monitor bees' living conditions by equipping beehives with sensors. The data recorded by these hives can be analyzed by machine learning models to le…
SimLoss: Class Similarities in Cross Entropy
Konstantin Kobs, Michael Steininger, Albin Zehe +2
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an in…