Search Results for author:
Found 7 papers, 3 papers with code
Robust T-Loss for Medical Image Segmentation
Our results provide strong evidence that the T-Loss is a promising alternative for medical image segmentation where high levels of noise or outliers in the dataset are a typical phenomenon in practice.
Towards Reliable Dermatology Evaluation Benchmarks
Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates.
Multi-Coil MRI Reconstruction Challenge -- Assessing Brain MRI Reconstruction Models and their Generalizability to Varying Coil Configurations
Deep-learning-based brain magnetic resonance imaging (MRI) reconstruction methods have the potential to accelerate the MRI acquisition process.
STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains
We propose to predict the uncertainty of pseudo labels and integrate it in the training process with an uncertainty-guided loss function to highlight labels with high certainty.
SelfClean: A Self-Supervised Data Cleaning Strategy
Most benchmark datasets for computer vision contain irrelevant images, near duplicates, and label errors.
Assessing Guest Nationality Composition from Hotel Reviews
Many hotels target guest acquisition efforts to specific markets in order to best anticipate individual preferences and needs of their guests.
Hyperbolic Metric Learning for Visual Outlier Detection
Out-Of-Distribution (OOD) detection is critical to deploy deep learning models in safety-critical applications.
