most citedNICER: Aesthetic Image Enhancement with Humans in the Loop

2 citations · 2 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2022

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…

cs.CV2022

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…

cs.CV2022

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…

cs.HC20202 cited

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…

cs.LG2020

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…

cs.LG2020

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…