Search Results for author:
Found 8 papers, 3 papers with code
InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images
Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language.
Semi-unsupervised Learning for Time Series Classification
Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually.
Do Different Deep Metric Learning Losses Lead to Similar Learned Features?
In this paper, we investigate this by conducting a two-step analysis to extract and compare the learned visual features of the same model architecture trained with different loss functions: First, we compare the learned features on the pixel level by correlating saliency maps of the same input images.
Anomaly Detection in Beehives: An Algorithm Comparison
Sensor-equipped beehives allow monitoring the living conditions of bees.
Deep Learning for Climate Model Output Statistics
Climate models are an important tool for the assessment of prospective climate change effects but they suffer from systematic and representation errors, especially for precipitation.
Anomaly Detection in Beehives using Deep Recurrent Autoencoders
Precision beekeeping allows to monitor bees' living conditions by equipping beehives with sensors.
SimLoss: Class Similarities in Cross Entropy
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally.
MapLUR: Exploring a new Paradigm for Estimating Air Pollution using Deep Learning on Map Images
In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data.
